© 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. 75240
    Prev
    Next
    INDEX
    Explanations

    references to competitive sports events and athletic achievements

    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
     handleError
    -0.07
    çŁ³
    -0.06
    roid
    -0.06
    avanaugh
    -0.06
    sdale
    -0.06
    _IW
    -0.06
    епÑĤи
    -0.06
    enÃŃ
    -0.06
    iese
    -0.06
     Muscle
    -0.06
    POSITIVE LOGITS
     Ski
    0.09
     ski
    0.09
    Snow
    0.08
     snow
    0.08
     Snow
    0.08
    _firestore
    0.07
     skiing
    0.07
    snow
    0.07
    track
    0.07
    _fence
    0.07
    Activations Density 0.002%

    No Known Activations