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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 6799
    Prev
    Next
    INDEX
    Explanations

    ;

    np_max-act · gemini-2.0-flash

    This neuron is specialized to detect the JavaScript `"use strict"` directive (the strict‐mode pragma) at the top of a file.

    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
    .peer
    -0.07
    hold
    -0.06
    관리
    -0.06
    Ob
    -0.06
    orpion
    -0.06
     Consent
    -0.06
     بيت
    -0.06
    šší
    -0.06
     fend
    -0.06
    ['_
    -0.06
    POSITIVE LOGITS
     formerly
    0.07
    امة
    0.06
    rouw
    0.06
     Ontario
    0.06
     huis
    0.06
     abilities
    0.06
     Sergeant
    0.06
    atz
    0.06
    639
    0.06
    ğan
    0.06
    Activations Density 0.000%

    No Known Activations