© 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. 90660
    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
    illez
    -0.07
     hete
    -0.06
    ickness
    -0.06
    ÑģÑĤе
    -0.06
    иÑĪ
    -0.06
    iez
    -0.06
    avana
    -0.06
    stru
    -0.06
    gv
    -0.06
    ekt
    -0.06
    POSITIVE LOGITS
    unca
    0.07
    ç´į
    0.06
    ิà¸Ĺ
    0.06
    èŃľ
    0.06
    ylko
    0.06
    raq
    0.06
    Outcome
    0.06
     Vinci
    0.06
    _factory
    0.06
    liest
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.