© 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. 16298
    Prev
    Next
    INDEX
    Explanations

    references to virtual learning adaptations and community support initiatives

    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
    askell
    -0.07
    icias
    -0.06
    Pooling
    -0.06
    idth
    -0.06
     Rub
    -0.06
    unde
    -0.06
     unf
    -0.06
    à¤łà¤¨
    -0.06
     Covid
    -0.06
     coronavirus
    -0.06
    POSITIVE LOGITS
     virtual
    0.11
    virtual
    0.10
     Virtual
    0.09
    Virtual
    0.09
    _virtual
    0.08
    -online
    0.08
    remote
    0.07
    abad
    0.07
    .virtual
    0.07
     Hats
    0.06
    Activations Density 0.020%

    No Known Activations