© 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. 58584
    Prev
    Next
    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash

    The neuron fires on the “<” that begins a bracketed import (e.g. the “<” in #import <…>) in Objective-C include statements.

    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
     editions
    -0.07
     Pron
    -0.07
     prec
    -0.07
    ตะ
    -0.07
    (javax
    -0.06
    _LOCAL
    -0.06
     geht
    -0.06
     Edition
    -0.06
    goto
    -0.06
    	SET
    -0.06
    POSITIVE LOGITS
    orrect
    0.06
    .unshift
    0.06
     ör
    0.06
     Farage
    0.06
     thaw
    0.06
    -second
    0.06
     duplicated
    0.06
     fuera
    0.06
    hin
    0.06
    izar
    0.06
    Activations Density 0.001%

    No Known Activations