© 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. 95101
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "exception" and related forms

    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
    obra
    -0.07
    /doc
    -0.06
    rif
    -0.06
    iza
    -0.06
    ilo
    -0.06
    737
    -0.06
     Mour
    -0.06
    reh
    -0.06
    ãģ¾ãģŁ
    -0.06
     Ost
    -0.06
    POSITIVE LOGITS
    ary
    0.08
    (exception
    0.07
    ált
    0.07
    antly
    0.07
    ein
    0.07
    nement
    0.07
    edn
    0.07
    edl
    0.07
     few
    0.07
    InstanceState
    0.07
    Activations Density 0.001%

    No Known Activations