© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 84007
    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
    ervo
    -0.08
    rzy
    -0.08
    anko
    -0.07
    .rawValue
    -0.07
     kys
    -0.07
    aval
    -0.07
    ä»ĺãģij
    -0.07
    ikal
    -0.07
    ãģ£
    -0.07
    rei
    -0.07
    POSITIVE LOGITS
     girls
    0.08
     Girls
    0.08
     village
    0.07
     Village
    0.07
     Dreams
    0.07
    Girls
    0.06
     Municip
    0.06
     meisjes
    0.06
    -girl
    0.06
     women
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.