© 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. 83167
    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
    766
    -0.07
    dıģında
    -0.07
    ntax
    -0.07
    _imag
    -0.07
     :↵↵↵↵
    -0.07
    846
    -0.06
    334
    -0.06
     Slack
    -0.06
    _Framework
    -0.06
    본
    -0.06
    POSITIVE LOGITS
     endpoints
    0.06
    onte
    0.06
    iele
    0.06
    abras
    0.06
    angered
    0.06
    ìĦŃ
    0.06
    ↵
    0.06
    essor
    0.06
    ante
    0.06
    اÙī
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.