© 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. 30306
    Prev
    Next
    INDEX
    Explanations

    numerical statistics related to performance in sports

    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
    esteem
    -0.06
     SavaÅŁÄ±
    -0.06
    δή
    -0.06
    ester
    -0.06
    ishes
    -0.06
     glo
    -0.06
     McN
    -0.05
    ulla
    -0.05
     Wallace
    -0.05
     Mov
    -0.05
    POSITIVE LOGITS
    ä»Ĭå¹´
    0.13
     already
    0.09
    already
    0.09
     season
    0.09
    Already
    0.09
    early
    0.08
    aison
    0.08
     currently
    0.08
     early
    0.08
     ÑĤекÑĥÑī
    0.08
    Activations Density 0.052%

    No Known Activations