© 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. 5182
    Prev
    Next
    INDEX
    Explanations

    references to specific years, particularly in the format of four digits

    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
     tailor
    -0.07
    {{{
    -0.05
    entimes
    -0.05
    .mo
    -0.05
    appers
    -0.05
    Ìģ
    -0.05
    è·
    -0.05
    ç¬Ķ
    -0.05
     Si
    -0.05
     si
    -0.05
    POSITIVE LOGITS
    avax
    0.07
     Fore
    0.07
    SqlParameter
    0.07
    èªł
    0.07
    avicon
    0.07
     åĨĨ
    0.07
    yonel
    0.07
    #=
    0.07
    cü
    0.07
    icket
    0.07
    Activations Density 0.017%

    No Known Activations