© 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. 70965
    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
    olina
    -0.08
    asha
    -0.07
    ulan
    -0.07
    etsk
    -0.07
    862
    -0.06
    arter
    -0.06
    umpt
    -0.06
    isu
    -0.06
    缮ãĤĴ
    -0.06
    olan
    -0.06
    POSITIVE LOGITS
     cadre
    0.06
     Publication
    0.06
    irit
    0.06
     rem
    0.06
     Rem
    0.06
    ึà¸ģ
    0.05
    à¸ľ
    0.05
    neh
    0.05
     underst
    0.05
     prof
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.