© 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 EvalsExportsAPI 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. 27-RESID-POST-AA
    11. 100013
    Prev
    Next
    INDEX
    Explanations

    say "first name"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     competitors
    -0.07
     méthode
    -0.07
    (tag
    -0.07
    광고
    -0.06
    contexts
    -0.06
     Lock
    -0.06
    _reports
    -0.06
    考试
    -0.06
    스의
    -0.06
     Payment
    -0.06
    POSITIVE LOGITS
    ﻟ�
    0.07
    .BOTTOM
    0.07
    OTTOM
    0.07
     multiplied
    0.06
    .learn
    0.06
     DataColumn
    0.06
    حی
    0.06
    _guid
    0.06
    .ll
    0.06
    CCI
    0.06
    Activations Density 0.181%

    No Known Activations