© 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. 17-LLAMASCOPE-RES-131K
    11. 56412
    Prev
    Next
    INDEX
    Explanations

    references to the second half of sports events

    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
    APON
    -0.07
    ÏĢλα
    -0.07
    apot
    -0.07
    esan
    -0.06
    kün
    -0.06
    ìĦ¼
    -0.06
    gettext
    -0.06
    é±
    -0.06
    mite
    -0.06
    uyá»ħn
    -0.06
    POSITIVE LOGITS
    879
    0.07
     of
    0.07
    s
    0.07
    ime
    0.07
    cular
    0.07
    ular
    0.06
    _Lean
    0.06
    aign
    0.06
    orris
    0.06
    agner
    0.06
    Activations Density 0.004%

    No Known Activations