© 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 EvalsExportsinterp-engineNEWAPI 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. 17951
    Prev
    Next
    INDEX
    Explanations

    code and regex

    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
     dismissal
    -0.07
    -query
    -0.06
     Dak
    -0.06
    In
    -0.06
    itä
    -0.06
     Teen
    -0.06
    ्तम
    -0.06
     ऑ
    -0.06
     jointly
    -0.06
     mujer
    -0.06
    POSITIVE LOGITS
    (()=>
    0.07
    \controllers
    0.07
     menší
    0.07
    .regex
    0.06
     deflect
    0.06
     teb
    0.06
    徒歩
    0.06
     acı
    0.06
     тих
    0.06
     означа
    0.06
    Activations Density 0.008%

    No Known Activations