© 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. 19-RESID-POST-AA
    6. 71600
    Prev
    Next
    INDEX
    Explanations

    cast of characters

    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
     является
    -0.07
    chalk
    -0.07
    dan
    -0.06
    kw
    -0.06
     injections
    -0.06
    Blank
    -0.06
    皇
    -0.06
     caracter
    -0.06
     بق
    -0.06
     leaps
    -0.06
    POSITIVE LOGITS
     establish
    0.06
     iVar
    0.06
    Matchers
    0.06
     group
    0.06
     fittings
    0.06
    ahrung
    0.06
    !!}↵
    0.06
    ční
    0.06
     onLoad
    0.06
    ΟΥΣ
    0.06
    Activations Density 0.054%

    No Known Activations