© 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. 11-RESID-POST-AA
    11. 124580
    Prev
    Next
    INDEX
    Explanations

    in

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ホ
    -0.07
     pirates
    -0.06
     WAV
    -0.06
     voir
    -0.06
     metrů
    -0.06
     izin
    -0.06
     nehmen
    -0.06
    Yo
    -0.06
     nuevos
    -0.06
     بهترین
    -0.06
    POSITIVE LOGITS
    lessness
    0.07
    bur
    0.07
    stances
    0.07
    л
    0.06
     revolt
    0.06
    verification
    0.06
     miles
    0.06
     communicating
    0.06
    (signal
    0.06
    励
    0.06
    Activations Density 0.001%

    No Known Activations