© 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. 81470
    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
    εÏħ
    -0.07
    isl
    -0.06
     Boy
    -0.06
    atten
    -0.06
     Berger
    -0.06
     Latter
    -0.05
     cour
    -0.05
     Levy
    -0.05
    oker
    -0.05
     attending
    -0.05
    POSITIVE LOGITS
     actionTypes
    0.08
    ΣΤ
    0.08
    -double
    0.07
    urch
    0.07
    rians
    0.07
    coration
    0.07
    ITO
    0.07
    stras
    0.07
    .stopPropagation
    0.07
    atype
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.