© 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. 107674
    Prev
    Next
    INDEX
    Explanations

    references to diseases and their unknown causes

    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
    uelle
    -0.07
    ikit
    -0.07
    loat
    -0.07
    bish
    -0.06
    ستÙĩ
    -0.06
    езда
    -0.06
     Arb
    -0.06
    .coords
    -0.06
    _BASIC
    -0.06
    xiv
    -0.06
    POSITIVE LOGITS
     mystery
    0.13
     mysterious
    0.11
     explanation
    0.10
     Mystery
    0.10
     baff
    0.10
     explanations
    0.10
     mysteries
    0.10
     Explanation
    0.09
     inexp
    0.09
     explain
    0.09
    Activations Density 0.039%

    No Known Activations