© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 25-LLAMASCOPE-RES-32K
    6. 15749
    Prev
    Next
    INDEX
    Explanations

    terms related to presidential elections and campaigns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    The neuron activates strongly for the word "Presidential" (and related forms like "presidential"), particularly in political and electoral contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    mentions of U.S. presidential politics—especially references to elections, campaigns, candidates, or the presidency.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yun
    -0.16
    fak
    -0.15
    fed
    -0.14
    èij£äºĭ
    -0.14
    jo
    -0.14
    ικα
    -0.14
    ÌĢ
    -0.13
    ithe
    -0.13
     tant
    -0.13
    ertoire
    -0.13
    POSITIVE LOGITS
     race
    0.24
     hopeful
    0.22
     Race
    0.20
    race
    0.20
    Race
    0.19
    _race
    0.17
    ty
    0.17
     campaign
    0.16
    ampaign
    0.16
     Primary
    0.16
    Activations Density 0.017%

    No Known Activations