© 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. 58617
    Prev
    Next
    INDEX
    Explanations

    conventional

    np_max-act · gemini-2.0-flash

    This neuron activates on the phrase “conventional wisdom,” signaling the detection of that specific idiomatic expression.

    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
     če
    -0.07
     Στο
    -0.06
    声
    -0.06
    arf
    -0.06
     Matth
    -0.06
     bra
    -0.06
     Aussie
    -0.06
    egan
    -0.06
    	mat
    -0.06
    (doc
    -0.06
    POSITIVE LOGITS
    enez
    0.06
     брон
    0.06
    Verified
    0.06
     HEAD
    0.06
    <>
    0.06
     villagers
    0.06
    _orientation
    0.06
    krom
    0.06
    ALLENG
    0.06
    なく
    0.06
    Activations Density 0.041%

    No Known Activations