© 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. 108126
    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
    ilder
    -0.07
    Ä±ÅŁÄ±k
    -0.07
    'gc
    -0.07
    grily
    -0.07
    ='".
    -0.07
    iais
    -0.06
    azu
    -0.06
    zug
    -0.06
    781
    -0.06
    putc
    -0.06
    POSITIVE LOGITS
    ;s
    0.07
    ffen
    0.07
     Andersen
    0.06
    orial
    0.06
    ault
    0.06
     recom
    0.06
    .retrieve
    0.06
    inal
    0.06
    »
    0.06
     pertinent
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.