© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 81893
    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
    quo
    -0.07
    DEX
    -0.07
    upa
    -0.07
    alo
    -0.07
    _INCREF
    -0.07
     ži
    -0.07
    .instructions
    -0.07
    olume
    -0.07
    .converter
    -0.07
    yan
    -0.07
    POSITIVE LOGITS
     hind
    0.06
     ministry
    0.06
     God
    0.06
    jin
    0.06
    919
    0.06
     He
    0.06
     jars
    0.06
     adrenaline
    0.06
     Col
    0.05
    jab
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.