© 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. 60836
    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
    Å
    -0.06
    ilde
    -0.06
     вп
    -0.06
     bree
    -0.06
    éı¡
    -0.06
    globals
    -0.06
    Ð
    -0.05
    asz
    -0.05
     Lester
    -0.05
    lıģına
    -0.05
    POSITIVE LOGITS
     esk
    0.09
    ÌĨ
    0.07
    Ìĥ
    0.07
    IDL
    0.07
     kari
    0.07
    sock
    0.07
    ç´ł
    0.06
    razier
    0.06
    IDEO
    0.06
    Ð¤ÐĽ
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.