© 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. 117624
    Prev
    Next
    INDEX
    Explanations

    the occurrence of certain numeric identifiers or references in the text

    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
    tml
    -0.07
    baugh
    -0.07
    indr
    -0.07
     æģ
    -0.07
    ulls
    -0.07
    qli
    -0.07
    gradable
    -0.07
    ctest
    -0.07
    nob
    -0.06
    olk
    -0.06
    POSITIVE LOGITS
     رئ
    0.06
    uiltin
    0.06
    è·
    0.06
    ipsis
    0.06
    ève
    0.06
     trio
    0.05
     forthcoming
    0.05
    ØŃØ«
    0.05
    ilion
    0.05
    Ãĭ
    0.05
    Activations Density 0.000%

    No Known Activations