© 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. 91911
    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
    mav
    -0.07
    ighb
    -0.07
    osemite
    -0.06
    кеÑĤ
    -0.06
    FromBody
    -0.06
     Punk
    -0.06
    opak
    -0.06
    pedia
    -0.06
    IID
    -0.06
     Erotik
    -0.06
    POSITIVE LOGITS
    /unit
    0.06
    istle
    0.06
    zo
    0.06
    .scalar
    0.06
     vac
    0.05
    _street
    0.05
     transitional
    0.05
     Vine
    0.05
     vital
    0.05
     Land
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.