© 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. 15-LLAMASCOPE-RES-131K
    11. 103909
    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
    oub
    -0.07
    hani
    -0.06
    oyer
    -0.06
     ham
    -0.06
    «
    -0.06
    letal
    -0.06
     erg
    -0.05
    utz
    -0.05
     stir
    -0.05
     er
    -0.05
    POSITIVE LOGITS
     EXEMPLARY
    0.08
     ogs
    0.07
     initComponents
    0.07
    vard
    0.07
    ÌĨ
    0.07
    inati
    0.07
    Conexion
    0.07
    olland
    0.07
    ugin
    0.07
     initState
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.