© 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. 41319
    Prev
    Next
    INDEX
    Explanations

    functions and methods related to string manipulation, particularly those that check for prefixes and substrings

    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
    utas
    -0.08
    aylight
    -0.07
    deaux
    -0.07
    ös
    -0.07
     "/";↵
    -0.07
    iyon
    -0.07
    ائÙĤ
    -0.07
    inox
    -0.07
    átis
    -0.07
    zeÅĦ
    -0.07
    POSITIVE LOGITS
    legate
    0.06
    478
    0.06
     subscribe
    0.06
     shr
    0.06
    099
    0.05
     wire
    0.05
     aut
    0.05
     ensemble
    0.05
    -ever
    0.05
     ref
    0.05
    Activations Density 0.015%

    No Known Activations