© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 121794
    Prev
    Next
    INDEX
    Explanations

    .js

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lean
    -0.06
    ORT
    -0.06
     stojí
    -0.06
     bind
    -0.06
     "":↵
    -0.06
    with
    -0.06
     ';↵
    -0.06
    /key
    -0.06
    _sat
    -0.06
     계약
    -0.06
    POSITIVE LOGITS
     Increased
    0.07
    NSInteger
    0.07
     UIKit
    0.07
     Connected
    0.06
    .QRect
    0.06
     Olomou
    0.06
    aptop
    0.06
    LEMENT
    0.06
    _bloc
    0.06
    	scroll
    0.06
    Activations Density 0.003%

    No Known Activations