© 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. 15-LLAMASCOPE-RES-131K
    11. 87340
    Prev
    Next
    INDEX
    Explanations

    numerical values related to measurements or parameters in scientific contexts

    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
    assi
    -0.09
     bát
    -0.08
    uko
    -0.07
    ãĢĤãĢĤ↵↵
    -0.07
    æľĭ
    -0.07
    ｡
    -0.07
    ÛĮزÛĮ
    -0.07
    ãĥĩãĤ£ãĤ¢
    -0.07
     %[
    -0.07
    ayet
    -0.07
    POSITIVE LOGITS
    MethodInfo
    0.07
    621
    0.06
    OI
    0.06
    /stdc
    0.06
    conti
    0.05
    lim
    0.05
    828
    0.05
    Transparent
    0.05
    797
    0.05
    ads
    0.05
    Activations Density 0.019%

    No Known Activations