© 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. 15495
    Prev
    Next
    INDEX
    Explanations

    expressions related to physiological changes and conditions

    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
    ially
    -0.08
    .Fat
    -0.08
    ensely
    -0.07
    ält
    -0.07
    ankan
    -0.07
    _sdk
    -0.07
    afort
    -0.07
    oland
    -0.07
    ãĥ«ãĤ¯
    -0.06
    itals
    -0.06
    POSITIVE LOGITS
     trend
    0.07
     boz
    0.06
     occurs
    0.06
     Bennett
    0.06
    ingen
    0.06
    212
    0.06
    OffsetTable
    0.06
    aton
    0.06
     of
    0.06
    -shift
    0.06
    Activations Density 0.052%

    No Known Activations