© 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. 95577
    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
    ales
    -0.07
    eln
    -0.06
     Carp
    -0.06
    aco
    -0.06
     Actor
    -0.06
    ilden
    -0.06
    .arch
    -0.06
    YT
    -0.06
    ylie
    -0.06
    ÏĢε
    -0.06
    POSITIVE LOGITS
    _eye
    0.07
    .eye
    0.07
    Vision
    0.07
     Vision
    0.07
     Lever
    0.07
     Eye
    0.07
     EXEMPLARY
    0.07
     vision
    0.07
     eye
    0.07
    eye
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.