© 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. 81543
    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
    izu
    -0.08
    orrent
    -0.07
    ÃŃÅ¡
    -0.07
    leme
    -0.07
    ripp
    -0.07
    åĬ
    -0.07
    aeda
    -0.07
    =".$_
    -0.07
     AssemblyCopyright
    -0.07
    licken
    -0.07
    POSITIVE LOGITS
     innocent
    0.06
     till
    0.06
     gentlemen
    0.06
    ,
    0.06
     exped
    0.06
     hi
    0.05
     dv
    0.05
    ber
    0.05
     /
    0.05
     ·
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.