© 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. 61378
    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
    elle
    -0.07
    'gc
    -0.07
    _CPP
    -0.06
    اذ
    -0.06
    anyl
    -0.06
     Damen
    -0.06
     Randall
    -0.06
    iku
    -0.06
    ele
    -0.06
     surely
    -0.06
    POSITIVE LOGITS
    chter
    0.08
     Farr
    0.07
     indiv
    0.06
     Pot
    0.06
     impass
    0.06
     tens
    0.06
     potentially
    0.06
     seper
    0.06
    ocz
    0.06
     factor
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.