© 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. 119097
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate comparisons and contrasts

    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
    achen
    -0.09
    esktop
    -0.07
    ITO
    -0.07
    cult
    -0.06
    Forever
    -0.06
    upply
    -0.06
    Ñĥже
    -0.06
     etc
    -0.06
    รà¸Ńà¸ļ
    -0.06
    och
    -0.06
    POSITIVE LOGITS
     oneself
    0.07
     someone
    0.07
     freshly
    0.07
     somebody
    0.07
    CMD
    0.07
     комÑĥ
    0.06
     ë°Ķë¡ľ
    0.06
    {return
    0.06
    æĿ¥èĩª
    0.06
    someone
    0.06
    Activations Density 0.018%

    No Known Activations