© 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. 124671
    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
    rex
    -0.08
    iggins
    -0.08
    kap
    -0.08
    кав
    -0.08
    ¼
    -0.07
    emoc
    -0.07
    UX
    -0.07
    emachine
    -0.07
    regar
    -0.07
    koli
    -0.07
    POSITIVE LOGITS
     *
    0.06
     expertise
    0.06
    ullen
    0.06
     Altern
    0.05
    coming
    0.05
     ("
    0.05
     Ale
    0.05
    UpdateTime
    0.05
     fucking
    0.05
    193
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.