© 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. 15-RESID-POST-AA
    11. 29935
    Prev
    Next
    INDEX
    Explanations

    words with suffix "ive"/"ative"

    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
     regions
    -0.08
     January
    -0.07
     end
    -0.07
     region
    -0.07
     day
    -0.07
     began
    -0.07
     screenshot
    -0.07
     December
    -0.07
     ears
    -0.07
     Region
    -0.07
    POSITIVE LOGITS
    imu
    0.08
    itive
    0.08
    bé
    0.08
    cce
    0.08
    jie
    0.08
    ыва
    0.08
    ıcı
    0.08
    .jsoup
    0.08
    dee
    0.08
    وفي
    0.08
    Activations Density 0.163%

    No Known Activations