© 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. 128694
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and activities related to culture or lifestyle

    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
    etc
    -0.09
    ixel
    -0.07
    -haspopup
    -0.07
    abei
    -0.07
    /etc
    -0.07
    holm
    -0.07
     ðŁĻĤ↵↵
    -0.07
    éĤ£ç§į
    -0.07
    ساÙĨÛĮ
    -0.07
    iceps
    -0.07
    POSITIVE LOGITS
     Tune
    0.07
     their
    0.06
    åŃĿ
    0.06
    hoff
    0.06
     his
    0.06
     Doc
    0.06
     reveals
    0.05
    QS
    0.05
     Auto
    0.05
     tune
    0.05
    Activations Density 0.006%

    No Known Activations