© 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. 86229
    Prev
    Next
    INDEX
    Explanations

    references to stains and soil marks on various items

    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
    ystore
    -0.08
    ipa
    -0.08
     Oc
    -0.06
    ocode
    -0.06
     oc
    -0.06
    ypi
    -0.06
    /watch
    -0.06
    /root
    -0.06
    834
    -0.06
    ibox
    -0.06
    POSITIVE LOGITS
    ëĿ½
    0.07
     outs
    0.07
    ooks
    0.07
     Eig
    0.07
    æĸ
    0.07
    INCT
    0.07
    ooter
    0.06
    lint
    0.06
    cast
    0.06
    unda
    0.06
    Activations Density 0.015%

    No Known Activations