© 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. 94317
    Prev
    Next
    INDEX
    Explanations

    phrases indicating potential improvements or suggestions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    prompt
    -0.07
    rada
    -0.07
    RIX
    -0.06
     genu
    -0.06
    elan
    -0.06
    ritt
    -0.06
    elage
    -0.06
    vette
    -0.06
    667
    -0.06
    eks
    -0.06
    POSITIVE LOGITS
     improvement
    0.10
     improve
    0.09
     Improvement
    0.09
     improved
    0.08
     Improve
    0.08
     improving
    0.08
    jit
    0.08
     improves
    0.07
     better
    0.07
    better
    0.07
    Activations Density 0.062%

    No Known Activations