© 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. 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. 58301
    Prev
    Next
    INDEX
    Explanations

    cooking instructions

    np_max-act · gemini-2.0-flash

    This neuron fires on cooking‐instruction verbs—imperative action words like “sauté,” “heat,” “add,” “cut,” etc., in recipe steps.

    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
     FETCH
    -0.07
    _constraints
    -0.07
     propre
    -0.07
    �
    -0.06
    frontend
    -0.06
    DataManager
    -0.06
    /lic
    -0.06
    _binary
    -0.06
    ,NULL
    -0.06
    Raise
    -0.06
    POSITIVE LOGITS
     ๆ
    0.06
     WW
    0.06
     Amendments
    0.06
    psc
    0.06
    _rng
    0.06
    .dt
    0.06
    自
    0.06
    öffent
    0.06
     име
    0.06
    (auth
    0.06
    Activations Density 0.012%

    No Known Activations