© 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. 81228
    Prev
    Next
    INDEX
    Explanations

    references to specific countries or geographic locations

    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
    places
    -0.09
    nd
    -0.07
    857
    -0.07
    prec
    -0.06
    лÑıн
    -0.06
    æѤ
    -0.06
    868
    -0.06
    bies
    -0.06
    /compiler
    -0.06
    linger
    -0.06
    POSITIVE LOGITS
    oop
    0.08
    ائر
    0.07
    ../../../
    0.07
    don
    0.07
    ultz
    0.07
    ension
    0.07
    gone
    0.07
    .gdx
    0.07
    gli
    0.07
    lags
    0.07
    Activations Density 0.031%

    No Known Activations