© 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. 4630
    Prev
    Next
    INDEX
    Explanations

    concepts related to regenerative medicine and stem cell research

    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
    anje
    -0.07
    hurst
    -0.07
    inqu
    -0.07
    MMdd
    -0.06
    odash
    -0.06
     spol
    -0.06
    elop
    -0.06
    kad
    -0.06
    upo
    -0.06
    croft
    -0.06
    POSITIVE LOGITS
     plur
    0.08
     repro
    0.07
     recap
    0.07
     donor
    0.07
     culture
    0.07
     som
    0.07
     mouse
    0.07
     tot
    0.07
     cells
    0.06
     human
    0.06
    Activations Density 0.005%

    No Known Activations