© 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. 86467
    Prev
    Next
    INDEX
    Explanations

    genes and proteins associated with cellular functions and signaling pathways

    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
    opi
    -0.07
    ↵↵
    -0.07
    oner
    -0.07
    idis
    -0.07
     steam
    -0.06
    DEPTH
    -0.06
    hdl
    -0.06
     èij
    -0.06
     purge
    -0.06
    inan
    -0.06
    POSITIVE LOGITS
     kinase
    0.10
     Cancer
    0.07
     cancer
    0.07
     phosphory
    0.07
     Src
    0.07
     Ùģس
    0.07
     phosph
    0.07
    è°ĥ
    0.06
     Batter
    0.06
    Src
    0.06
    Activations Density 0.013%

    No Known Activations