© 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. 29965
    Prev
    Next
    INDEX
    Explanations

    skills and experiences related to teaching, management, and collaboration

    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
    erval
    -0.07
    ellas
    -0.07
    otton
    -0.07
    ême
    -0.06
    ngle
    -0.06
     Agencies
    -0.06
    errer
    -0.06
    émon
    -0.06
    irie
    -0.06
    itori
    -0.06
    POSITIVE LOGITS
     people
    0.07
    people
    0.07
    .openConnection
    0.06
    SError
    0.06
    essim
    0.06
    ropolitan
    0.06
    aramel
    0.06
     webpage
    0.06
    andard
    0.06
    DC
    0.06
    Activations Density 0.053%

    No Known Activations