© 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. 75198
    Prev
    Next
    INDEX
    Explanations

    details related to event scheduling and participation

    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
     CDs
    -0.06
     locally
    -0.06
    758
    -0.05
    ughs
    -0.05
     bass
    -0.05
     DVD
    -0.05
     fore
    -0.05
     ming
    -0.05
    Visitor
    -0.05
     infl
    -0.05
    POSITIVE LOGITS
     virtual
    0.15
    virtual
    0.14
     Virtual
    0.13
    _virtual
    0.13
    Virtual
    0.12
    .virtual
    0.11
     Zoom
    0.11
    VIRTUAL
    0.10
    zoom
    0.10
    irtual
    0.10
    Activations Density 0.067%

    No Known Activations