© 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. 20024
    Prev
    Next
    INDEX
    Explanations

    member

    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
    Charge
    -0.07
    .clip
    -0.07
    _sv
    -0.06
    istle
    -0.06
     survival
    -0.06
    _dt
    -0.06
     dau
    -0.06
     sideline
    -0.06
     dex
    -0.06
     milk
    -0.06
    POSITIVE LOGITS
    ідно
    0.08
     урок
    0.07
    OptionsItemSelected
    0.07
    oupper
    0.07
    objectManager
    0.07
    %p
    0.07
     meilleurs
    0.06
    (dirname
    0.06
    definitions
    0.06
    [type
    0.06
    Activations Density 0.050%

    No Known Activations