© 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. 83041
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     aforementioned
    -0.06
    _FMT
    -0.06
    ç
    -0.06
     seper
    -0.06
    amoto
    -0.06
     Simpsons
    -0.06
    -margin
    -0.06
     &
    -0.06
    ampo
    -0.05
     roommate
    -0.05
    POSITIVE LOGITS
     коли
    0.07
    oins
    0.07
     ÙħعÙĦ
    0.07
    och
    0.07
    uggle
    0.07
     cái
    0.07
    \param
    0.06
    Unnamed
    0.06
     gad
    0.06
    inel
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.