© 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. 41338
    Prev
    Next
    INDEX
    Explanations

    themes related to migration and cultural identity

    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
    oog
    -0.07
    302
    -0.06
    äft
    -0.06
    ffield
    -0.06
    ystone
    -0.06
    fty
    -0.06
    530
    -0.06
    .googleapis
    -0.06
    stown
    -0.06
    POSITIVE LOGITS
    _PID
    0.08
    ounter
    0.08
    /dc
    0.08
    ëıĦê°Ģ
    0.08
    باش
    0.08
     ÑĨÑİ
    0.07
    пÑĸд
    0.07
    ì§ĢëıĦ
    0.07
    ãĤ
    0.07
    ãĥ
    0.07
    Activations Density 0.187%

    No Known Activations