© 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. 105416
    Prev
    Next
    INDEX
    Explanations

    statements related to user requests or actions in a programming context

    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
     tend
    -0.07
    UTC
    -0.06
     favorite
    -0.06
     your
    -0.06
    ίÏĥ
    -0.06
     often
    -0.06
    sı
    -0.06
     yourself
    -0.06
    .Try
    -0.06
    uvo
    -0.06
    POSITIVE LOGITS
     بتÙĪاÙĨ
    0.08
     preferably
    0.07
     somehow
    0.07
    roe
    0.07
    indow
    0.07
    abra
    0.07
    hind
    0.07
    lish
    0.07
    bote
    0.07
    -automatic
    0.07
    Activations Density 0.020%

    No Known Activations