© 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 (Instruct)
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 56271
    Prev
    Next
    INDEX
    Explanations

    pronouns

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    马
    -0.06
     جديدة
    -0.06
     <![
    -0.06
    -toggle
    -0.06
     actionPerformed
    -0.06
    FL
    -0.05
    �n
    -0.05
    ">$
    -0.05
    )+↵
    -0.05
     VER
    -0.05
    POSITIVE LOGITS
    CLUDED
    0.08
    <Class
    0.07
     plaisir
    0.07
    Friend
    0.07
    olation
    0.07
     blah
    0.07
     Trav
    0.07
    roker
    0.06
     ště
    0.06
    fid
    0.06
    Activations Density 0.042%

    No Known Activations