© 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. 1632
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to stem cell research and transplantation

    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
    811
    -0.07
    amax
    -0.06
    atura
    -0.06
    andler
    -0.06
    pector
    -0.06
    idget
    -0.06
     Sala
    -0.06
    ubber
    -0.06
    lemn
    -0.06
    uki
    -0.06
    POSITIVE LOGITS
    ãģĹãĤĩ
    0.08
     donor
    0.07
    DSA
    0.07
    CharArray
    0.07
    êu
    0.07
    _KIND
    0.07
    GRA
    0.07
     immune
    0.06
     tslib
    0.06
    ãĤīãģı
    0.06
    Activations Density 0.027%

    No Known Activations