© 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. 11-RESID-POST-AA
    11. 79591
    Prev
    Next
    INDEX
    Explanations

    (

    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
    NX
    -0.07
     Far
    -0.06
     Magn
    -0.06
     North
    -0.06
     Bour
    -0.06
     flick
    -0.06
     CONVERT
    -0.06
     Gos
    -0.06
     operating
    -0.06
    VEN
    -0.06
    POSITIVE LOGITS
    .EntityFramework
    0.07
    甚至
    0.07
    */
↵
    0.07
    чины
    0.06
    :indexPath
    0.06
     회
    0.06
     można
    0.06
    docker
    0.06
    δρα
    0.06
    genre
    0.06
    Activations Density 0.000%

    No Known Activations