© 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. 95088
    Prev
    Next
    INDEX
    Explanations

    details about medical recovery processes and surgical interventions

    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
    clin
    -0.06
    avian
    -0.06
    olygon
    -0.06
    barang
    -0.06
    ERAL
    -0.06
     bÃło
    -0.06
    .Fields
    -0.06
     Abort
    -0.06
    Abort
    -0.06
     Dil
    -0.06
    POSITIVE LOGITS
     recovery
    0.10
     post
    0.10
     Recovery
    0.09
    Post
    0.08
     recuper
    0.08
     Post
    0.08
    _recovery
    0.08
     recover
    0.08
    post
    0.08
     POST
    0.08
    Activations Density 0.011%

    No Known Activations