© 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. 78294
    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
    edor
    -0.07
     detriment
    -0.07
    itone
    -0.07
    otal
    -0.06
    ãĥ¤
    -0.06
    ibern
    -0.06
     Worldwide
    -0.06
    å°ļ
    -0.06
    à¸ĵ
    -0.06
    ridged
    -0.06
    POSITIVE LOGITS
    éric
    0.07
    Ñĵ
    0.07
     cris
    0.06
    apus
    0.06
     Strom
    0.06
     Fog
    0.06
    گز
    0.06
    olec
    0.06
    ppy
    0.06
    wat
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.