© 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. 27436
    Prev
    Next
    INDEX
    Explanations

    references to black and brown cultural identity and heritage

    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
    _CUR
    -0.06
    875
    -0.06
     computer
    -0.06
    amba
    -0.06
    computer
    -0.06
     Warp
    -0.06
    zych
    -0.06
    615
    -0.06
    atte
    -0.06
    ampo
    -0.06
    POSITIVE LOGITS
     space
    0.07
     safest
    0.07
     spaces
    0.07
    aÄĩ
    0.06
    Æ¡i
    0.06
    gages
    0.06
    _extensions
    0.06
     prec
    0.06
    rawer
    0.06
    webtoken
    0.06
    Activations Density 0.001%

    No Known Activations