© 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. 124270
    Prev
    Next
    INDEX
    Explanations

    verbs and actions related to planning and processes

    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
    redits
    -0.07
    ussy
    -0.07
    erable
    -0.07
    uilder
    -0.07
    kle
    -0.07
    //{{
    -0.07
     nues
    -0.07
    Ậ
    -0.07
    زش
    -0.06
    redirectTo
    -0.06
    POSITIVE LOGITS
    çļĦæĺ¯
    0.07
     lassen
    0.07
    cona
    0.06
    pone
    0.06
    ifferent
    0.06
    äºĨä¸Ģ
    0.06
    -prepend
    0.06
     different
    0.06
     various
    0.06
     Ñģобой
    0.06
    Activations Density 0.049%

    No Known Activations