© 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. 93232
    Prev
    Next
    INDEX
    Explanations

    iterations in loops and counters used in programming

    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
    imity
    -0.08
    utenberg
    -0.07
    ults
    -0.07
    اساÙĨ
    -0.07
    nothrow
    -0.07
    plits
    -0.07
     Gin
    -0.07
     Tam
    -0.07
    opyright
    -0.06
    ioso
    -0.06
    POSITIVE LOGITS
    ++;↵
    0.07
    ++;↵↵
    0.07
    ++;
    0.06
    kins
    0.06
    olor
    0.06
     dere
    0.06
    arah
    0.06
    дина
    0.06
    psc
    0.06
    strup
    0.06
    Activations Density 0.009%

    No Known Activations