© 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. 95385
    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
    upert
    -0.07
     плен
    -0.06
    æİĪ
    -0.06
    roy
    -0.06
    енз
    -0.06
     зал
    -0.06
     Invisible
    -0.06
     createState
    -0.06
     Tham
    -0.06
    ä»°
    -0.06
    POSITIVE LOGITS
     convenience
    0.07
     Convenience
    0.07
    isches
    0.06
    ecut
    0.06
     hypo
    0.06
     proposal
    0.06
    zÅij
    0.06
     Shore
    0.06
    teri
    0.06
    .tb
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.