© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 84555
    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
    dle
    -0.07
    ests
    -0.07
     tanks
    -0.06
    idf
    -0.06
    stoup
    -0.06
    ä»ģ
    -0.06
     Tanks
    -0.06
    bis
    -0.06
    legate
    -0.06
    DIM
    -0.06
    POSITIVE LOGITS
    ÏĦÏģι
    0.06
    ï¸ı
    0.06
    ÌĤ
    0.06
     basic
    0.06
    orses
    0.06
     rang
    0.06
    ãĥ
    0.06
    ildo
    0.05
    à¸Ĺรà¸ĩ
    0.05
     thức
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.