© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 110792
    Prev
    Next
    INDEX
    Explanations

    computer code

    np_max-act · gemini-2.0-flash

    This neuron detects speaker‐ID tokens (the “NAME_n” labels and their following numeric values).

    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
     수도
    -0.07
    obel
    -0.06
    Solver
    -0.06
     Elliott
    -0.06
     ambigu
    -0.06
    尽
    -0.06
    actors
    -0.06
    英雄
    -0.06
    äsent
    -0.06
    axed
    -0.06
    POSITIVE LOGITS
     Song
    0.07
    	Return
    0.06
     kus
    0.06
    838
    0.06
    .constructor
    0.06
     dés
    0.06
     jas
    0.06
    ději
    0.06
    'http
    0.06
     validity
    0.06
    Activations Density 0.011%

    No Known Activations