© 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. 54689
    Prev
    Next
    INDEX
    Explanations

    domain-related terms and references to medical literature

    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
    ñana
    -0.07
     اÙĦØ£ØŃ
    -0.07
    ãĥŁãĥ¥
    -0.07
    plib
    -0.07
     Latter
    -0.06
    Æ°a
    -0.06
    callable
    -0.06
     pocket
    -0.06
    raud
    -0.06
    berman
    -0.06
    POSITIVE LOGITS
    ovan
    0.07
    _mD
    0.07
    _mE
    0.07
    anford
    0.07
    _tE
    0.07
    ovny
    0.07
    iad
    0.06
    _tA
    0.06
    _mB
    0.06
    hread
    0.06
    Activations Density 0.001%

    No Known Activations