© 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
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 118140
    Prev
    Next
    INDEX
    Explanations

    open reading frame

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /<?
    -0.06
    Attempting
    -0.06
    dns
    -0.06
     Š
    -0.06
     Qu
    -0.06
     Chim
    -0.06
    áz
    -0.06
     Rei
    -0.06
     dia
    -0.06
     nau
    -0.06
    POSITIVE LOGITS
     Sergeant
    0.07
    _USERNAME
    0.06
     seb
    0.06
    leitung
    0.06
    Avatar
    0.06
    verse
    0.06
     allocation
    0.06
    bands
    0.06
     sizi
    0.06
     hints
    0.06
    Activations Density 0.010%

    No Known Activations