© 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. 86375
    Prev
    Next
    INDEX
    Explanations

    specific terms and phrases related to team rosters and player positions

    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
    éĿ©
    -0.07
    огод
    -0.07
    äºŃ
    -0.07
    ضÙĦ
    -0.07
    pendicular
    -0.07
    ikan
    -0.06
    aign
    -0.06
    ammable
    -0.06
     noqa
    -0.06
    inkel
    -0.06
    POSITIVE LOGITS
     roster
    0.09
     lineup
    0.07
     list
    0.07
     adults
    0.06
     squad
    0.06
     U
    0.06
    _hover
    0.06
     line
    0.05
     consent
    0.05
     Adults
    0.05
    Activations Density 0.017%

    No Known Activations