© 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. 117111
    Prev
    Next
    INDEX
    Explanations

    instances of specific non-latin characters

    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
     Lac
    -0.07
    avic
    -0.07
    èĩ´
    -0.06
    346
    -0.06
    اØ
    -0.06
    otal
    -0.06
     Bac
    -0.06
    æŁĦ
    -0.06
     Bell
    -0.06
     interp
    -0.06
    POSITIVE LOGITS
    hoff
    0.08
    isNaN
    0.07
    chai
    0.07
    çī©
    0.07
    eker
    0.07
    NY
    0.07
    nels
    0.06
    nech
    0.06
    QUIT
    0.06
    hin
    0.06
    Activations Density 0.000%

    No Known Activations