© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 216
    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
    rrha
    -0.07
    .guard
    -0.07
    467
    -0.07
    cki
    -0.06
    assi
    -0.06
    vailability
    -0.06
    alan
    -0.06
     Schw
    -0.06
     Consumer
    -0.06
    agh
    -0.06
    POSITIVE LOGITS
     lou
    0.06
    .poi
    0.06
     CHK
    0.06
    .utf
    0.06
    _restart
    0.06
    /exec
    0.06
    /Peak
    0.06
    bero
    0.06
    ações
    0.06
     ConnectionState
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.