© 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. 85552
    Prev
    Next
    INDEX
    Explanations

    mentions of the "NC" (North Carolina) entity

    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
    othy
    -0.09
    utt
    -0.07
    ataka
    -0.07
    errals
    -0.07
    rijk
    -0.07
     اÙĦخاصة
    -0.07
    ewater
    -0.07
    aupt
    -0.07
    amak
    -0.07
    ngör
    -0.07
    POSITIVE LOGITS
    imb
    0.07
    il
    0.06
    _PUR
    0.06
    uden
    0.06
     NC
    0.06
     literature
    0.06
    bi
    0.06
     Pel
    0.06
     most
    0.06
    most
    0.06
    Activations Density 0.019%

    No Known Activations