© 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. 72067
    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
     surre
    -0.06
     Victims
    -0.06
    LEMENT
    -0.06
     such
    -0.05
    ÏĦα
    -0.05
    lok
    -0.05
    -plus
    -0.05
    Kit
    -0.05
     UIResponder
    -0.05
     Ryder
    -0.05
    POSITIVE LOGITS
    ktop
    0.09
    (Local
    0.07
    taboola
    0.07
    hora
    0.07
     odv
    0.07
    ippet
    0.07
    ampie
    0.07
    .asc
    0.07
    zeigen
    0.07
    à¹į
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.