© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 62043
    Prev
    Next
    INDEX
    Explanations

    instructions and comments related to coding tasks and adjustments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chten
    -0.07
    oret
    -0.06
     Dub
    -0.06
     Dude
    -0.06
    ynet
    -0.06
    ç§ij
    -0.06
    -thumbnails
    -0.06
    -eslint
    -0.06
    ($)
    -0.06
     Gee
    -0.06
    POSITIVE LOGITS
    -нибÑĥдÑĮ
    0.09
    bau
    0.08
     maybe
    0.08
     instead
    0.07
     perhaps
    0.07
    vil
    0.07
    apo
    0.07
     TODO
    0.07
     somehow
    0.07
    TODO
    0.07
    Activations Density 0.020%

    No Known Activations