© 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. 119633
    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
     Suff
    -0.07
    erge
    -0.07
     tent
    -0.07
    §
    -0.06
    .lab
    -0.06
    onth
    -0.06
    arehouse
    -0.06
     Lambert
    -0.06
     suff
    -0.06
     '(
    -0.06
    POSITIVE LOGITS
    ces
    0.07
    annes
    0.07
    Ñĩай
    0.07
     helicopt
    0.07
    ..↵↵↵↵
    0.07
    -inline
    0.06
    cock
    0.06
    Äįas
    0.06
    asco
    0.06
    others
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.