© 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. 30782
    Prev
    Next
    INDEX
    Explanations

    references to community engagement and acknowledgment of contributions

    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
    aring
    -0.07
    vid
    -0.07
    uth
    -0.06
    usz
    -0.06
    ж
    -0.06
    ros
    -0.06
    oot
    -0.06
    ets
    -0.06
    âijł
    -0.06
     in
    -0.06
    POSITIVE LOGITS
    $MESS
    0.07
     behalf
    0.07
     긴
    0.07
    ibold
    0.06
     adına
    0.06
     /*#__
    0.06
     baise
    0.06
    icket
    0.06
    CHED
    0.06
    _vue
    0.06
    Activations Density 0.006%

    No Known Activations