© 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. 117812
    Prev
    Next
    INDEX
    Explanations

    geographic locations or references to places

    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
    bast
    -0.07
    anine
    -0.07
    odor
    -0.07
    abor
    -0.07
    iler
    -0.06
    UNET
    -0.06
    resco
    -0.06
    uguay
    -0.06
    ÙĦÙĬات
    -0.06
    iras
    -0.06
    POSITIVE LOGITS
    bs
    0.08
    wide
    0.07
    egov
    0.06
    иной
    0.06
    sth
    0.06
     unf
    0.06
    زة
    0.06
    idue
    0.06
    ç«ĭ
    0.06
     VO
    0.06
    Activations Density 0.002%

    No Known Activations