© 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 EvalsExportsAPI 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. 119328
    Prev
    Next
    INDEX
    Explanations

    mentions of Afghanistan and related terms

    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
    ignum
    -0.07
    egg
    -0.07
     Fortune
    -0.07
    eum
    -0.07
    inct
    -0.07
    nox
    -0.07
    eson
    -0.07
    apan
    -0.07
    portlet
    -0.07
    اسب
    -0.06
    POSITIVE LOGITS
    (AF
    0.07
    447
    0.07
    rika
    0.06
    ذا
    0.06
    ektiv
    0.06
    elon
    0.06
    _INET
    0.06
    elik
    0.06
     Utt
    0.06
    -*-
    0.06
    Activations Density 0.009%

    No Known Activations