© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7-RESID-POST-AA
    11. 25001
    Prev
    Next
    INDEX
    Explanations

    Selective

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    非常
    -0.07
    ,img
    -0.06
     gaps
    -0.06
     pixel
    -0.06
     договору
    -0.06
     الزر
    -0.06
     グ
    -0.06
     constitute
    -0.06
     thems
    -0.06
     Gorgeous
    -0.06
    POSITIVE LOGITS
     selective
    0.14
    Selective
    0.11
     selectively
    0.10
    선
    0.08
     appointments
    0.06
     sele
    0.06
    .Optional
    0.06
     wrongful
    0.06
     CASE
    0.06
    SELECT
    0.06
    Activations Density 0.004%

    No Known Activations