Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 2-LLAMASCOPE-RES-32K
    6. 21817
    Prev
    Next
    INDEX
    Explanations

    references to the term "Dominion" and its variations, likely focusing on the context of energy companies or related industries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wilkinson
    -0.16
     Willis
    -0.15
     Sans
    -0.15
    EO
    -0.15
     Latin
    -0.15
    ais
    -0.14
     Palmer
    -0.14
     paren
    -0.14
    aise
    -0.13
     heavens
    -0.13
    POSITIVE LOGITS
    achinery
    0.16
    oeff
    0.16
    ACHI
    0.15
    igne
    0.15
    ombine
    0.15
    acci
    0.15
    [$_
    0.15
    presence
    0.14
    erd
    0.14
    agher
    0.14
    Activations Density 0.010%

    No Known Activations