© 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
    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. 104315
    Prev
    Next
    INDEX
    Explanations

    say "coaching"

    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
     conject
    -0.07
     fetish
    -0.06
     patrol
    -0.06
    اک
    -0.06
     PSA
    -0.06
    naissance
    -0.06
    ��
    -0.06
     одне
    -0.06
     guessing
    -0.06
    isting
    -0.06
    POSITIVE LOGITS
     HOL
    0.08
    Выб
    0.07
     chromium
    0.06
     MIN
    0.06
    publish
    0.06
    ���
    0.06
     جغراف
    0.06
    あった
    0.06
    ्वच
    0.06
     INCLUDED
    0.06
    Activations Density 0.143%

    No Known Activations