© 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. 30861
    Prev
    Next
    INDEX
    Explanations

    requests for volunteers and their qualifications

    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
    icers
    -0.07
    inton
    -0.07
    ocs
    -0.07
    uyu
    -0.07
    mouseleave
    -0.06
    ixin
    -0.06
    uyo
    -0.06
    svm
    -0.06
    achu
    -0.06
    odel
    -0.06
    POSITIVE LOGITS
     interested
    0.10
     spare
    0.08
     interest
    0.07
    968
    0.07
     expertise
    0.07
     Interested
    0.07
     interess
    0.07
     skills
    0.07
    713
    0.07
     intéress
    0.06
    Activations Density 0.012%

    No Known Activations