© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 27037
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the"

    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
    egend
    -0.07
    dlg
    -0.07
    úsqueda
    -0.06
    eggies
    -0.06
    fillType
    -0.06
    uito
    -0.06
    ruba
    -0.06
    isContained
    -0.06
    ей
    -0.06
    andin
    -0.06
    POSITIVE LOGITS
    aved
    0.07
    verts
    0.07
    tempts
    0.07
    oldt
    0.07
    ients
    0.07
    è°±
    0.06
    890
    0.06
    verted
    0.06
    ponible
    0.06
    ark
    0.06
    Activations Density 0.019%

    No Known Activations