© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 42789
    Prev
    Next
    INDEX
    Explanations

    terms related to medical treatment and mental health conditions

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    esters
    -0.08
    خص
    -0.08
    ehen
    -0.07
    inspection
    -0.07
    OCUS
    -0.07
    ÏĥÏĦε
    -0.07
    _VOID
    -0.07
    ixel
    -0.07
    ê³
    -0.07
    Ñĥж
    -0.06
    POSITIVE LOGITS
    /manage
    0.07
    inqu
    0.06
     Cohen
    0.06
     Turnbull
    0.06
    amentos
    0.06
     rec
    0.06
     for
    0.06
     Clayton
    0.06
    951
    0.06
    anitize
    0.06
    Activations Density 0.020%

    No Known Activations