© 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. 80229
    Prev
    Next
    INDEX
    Explanations

    high-activation timestamps and locations in the text

    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
    leon
    -0.07
     Thornton
    -0.06
    rif
    -0.06
    anik
    -0.06
    anders
    -0.06
    ÙĪاÙĦ
    -0.06
    ÙĪات
    -0.06
    razier
    -0.06
     âĹĦ
    -0.06
    uchos
    -0.06
    POSITIVE LOGITS
    ered
    0.08
    umin
    0.06
    ä¾
    0.06
    ÙIJÙĩ
    0.06
    ToProps
    0.06
    оÑĢÑĤÑĥ
    0.06
    edia
    0.06
    rella
    0.06
    unlink
    0.06
    .unregister
    0.06
    Activations Density 0.001%

    No Known Activations