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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 61687
    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
     hon
    -0.06
     Jennings
    -0.06
    cobra
    -0.06
    udic
    -0.05
     gut
    -0.05
     reb
    -0.05
     billed
    -0.05
    ylon
    -0.05
     xml
    -0.05
    evil
    -0.05
    POSITIVE LOGITS
    ziej
    0.08
    aghan
    0.08
    oner
    0.07
    yte
    0.07
    ationToken
    0.07
    ones
    0.07
    dre
    0.07
    LEGRO
    0.07
    596
    0.06
    949
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.