© 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. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 38366
    Prev
    Next
    INDEX
    Explanations

    job

    np_max-act · gemini-2.0-flash

    This neuron detects positive evaluations of performance, especially phrases praising someone’s “job” (e.g., “done a tremendous job”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     motivation
    -0.07
     smiled
    -0.06
    кул
    -0.06
    (static
    -0.06
    .lst
    -0.06
     апр
    -0.06
     Sauce
    -0.06
     امید
    -0.05
     sauces
    -0.05
     tutors
    -0.05
    POSITIVE LOGITS
     stint
    0.07
     зас
    0.07
     gracefully
    0.07
     ülkemiz
    0.07
    engine
    0.07
    架
    0.06
    ;';↵
    0.06
     Teams
    0.06
    =name
    0.06
     uży
    0.06
    Activations Density 0.012%

    No Known Activations