© 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. 17-LLAMASCOPE-RES-131K
    11. 105909
    Prev
    Next
    INDEX
    Explanations

    nicknames and titles associated with individuals

    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
    á»ķ
    -0.07
    ẩm
    -0.07
    immel
    -0.06
    ̣
    -0.06
    anden
    -0.06
    deme
    -0.06
    antz
    -0.06
    ctica
    -0.06
    _portal
    -0.06
    ylvania
    -0.06
    POSITIVE LOGITS
    -toggler
    0.07
     iron
    0.07
     Doctor
    0.07
     Captain
    0.07
     Iron
    0.06
     King
    0.06
    iss
    0.06
     guy
    0.06
    932
    0.06
     king
    0.06
    Activations Density 0.101%

    No Known Activations