© 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. 88838
    Prev
    Next
    INDEX
    Explanations

    references to specific areas on a sports field, particularly in relation to scoring opportunities

    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
     addCriterion
    -0.10
    zell
    -0.08
    dictions
    -0.07
    ithmetic
    -0.07
    esan
    -0.07
    над
    -0.07
    ONENT
    -0.07
    roperty
    -0.07
    ẻ
    -0.07
    нÑıÑĤи
    -0.07
    POSITIVE LOGITS
     resulting
    0.06
     Bou
    0.06
    yt
    0.06
    mark
    0.05
     Heap
    0.05
     Raven
    0.05
    -facing
    0.05
     imaginable
    0.05
    nable
    0.05
    fo
    0.05
    Activations Density 0.012%

    No Known Activations