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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 1-LLAMASCOPE-RES-32K
    6. 5671
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to voting and elections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 1-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _kind
    -0.16
    ville
    -0.15
    upertino
    -0.15
    acent
    -0.15
    ogan
    -0.14
    imens
    -0.14
    urer
    -0.14
    tif
    -0.14
    fid
    -0.14
    abus
    -0.14
    POSITIVE LOGITS
    lint
    0.15
    edException
    0.15
    ÃĹ↵↵
    0.15
    arrass
    0.14
    cripts
    0.14
    oop
    0.14
    Truthy
    0.14
    è³Ģ
    0.14
    èĢĥ
    0.14
    identity
    0.14
    Activations Density 1.137%

    No Known Activations