© 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. 80172
    Prev
    Next
    INDEX
    Explanations

    terms related to biological systems and their functions

    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
    лада
    -0.09
    ĥ
    -0.09
    /goto
    -0.08
    antino
    -0.08
    VOKE
    -0.08
    jÃŃž
    -0.08
     strav
    -0.08
    ån
    -0.07
    arde
    -0.07
    ifen
    -0.07
    POSITIVE LOGITS
     responsible
    0.10
    oret
    0.07
     located
    0.07
     situated
    0.06
     jury
    0.06
    located
    0.06
     Jury
    0.06
     hij
    0.06
     Dude
    0.06
     structures
    0.05
    Activations Density 0.031%

    No Known Activations