© 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. 80517
    Prev
    Next
    INDEX
    Explanations

    variations between things

    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
     refusal
    -0.06
    goal
    -0.06
     TensorFlow
    -0.06
    juan
    -0.06
     jack
    -0.06
    Seq
    -0.06
     sil
    -0.06
    네
    -0.06
    activex
    -0.06
    supply
    -0.06
    POSITIVE LOGITS
    =(
    0.07
    期間
    0.06
    -margin
    0.06
      	↵
    0.06
     appealing
    0.06
    (comb
    0.06
    previous
    0.06
    >[
    0.06
    (@
    0.06
    .SH
    0.06
    Activations Density 0.015%

    No Known Activations