© 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. 78714
    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
    ureau
    -0.08
    engin
    -0.08
    peria
    -0.07
    Inject
    -0.06
    ÅĻiv
    -0.06
     Tune
    -0.06
    念
    -0.06
    dlg
    -0.06
    essel
    -0.06
    eline
    -0.06
    POSITIVE LOGITS
    å¬
    0.07
    -transitional
    0.06
    .Manager
    0.06
    InSection
    0.06
    ago
    0.06
    .twig
    0.06
    &oacute
    0.06
    zyst
    0.06
    èĤ¥
    0.06
    itos
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.