© 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. 73632
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports teams and player assessments

    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
    ̣
    -0.07
    ÌĨ
    -0.07
    acter
    -0.07
    ActionResult
    -0.07
    /Gate
    -0.06
    icens
    -0.06
     guest
    -0.06
     cấp
    -0.06
    auer
    -0.06
    requestData
    -0.06
    POSITIVE LOGITS
     talent
    0.07
    atk
    0.07
     talented
    0.07
     personnel
    0.06
     Shah
    0.06
    _DU
    0.06
    ynes
    0.06
    lé
    0.06
    ovel
    0.06
    Assets
    0.06
    Activations Density 0.049%

    No Known Activations