© 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. 20155
    Prev
    Next
    INDEX
    Explanations

    connecting ideas

    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
    ducer
    -0.07
    Putting
    -0.07
    ibration
    -0.06
     slashed
    -0.06
    Str
    -0.06
    DAO
    -0.06
    ade
    -0.06
    Tables
    -0.06
    }.{
    -0.06
    Sal
    -0.06
    POSITIVE LOGITS
     obchod
    0.07
    merge
    0.07
    (on
    0.06
    earchBar
    0.06
     clockwise
    0.06
     ван
    0.06
     intox
    0.06
    ُون
    0.06
    一覧
    0.06
    .databind
    0.06
    Activations Density 0.088%

    No Known Activations