© 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. 35245
    Prev
    Next
    INDEX
    Explanations

    technical writing

    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
    vehicle
    -0.06
    рос
    -0.06
     tiles
    -0.06
    retched
    -0.06
     Norris
    -0.06
     Pert
    -0.06
    userId
    -0.06
    iments
    -0.06
    Pure
    -0.06
    _blocks
    -0.06
    POSITIVE LOGITS
    interested
    0.06
    ーボ
    0.06
    .Clamp
    0.06
     곧
    0.06
     لازم
    0.06
    /gtest
    0.06
     sab
    0.06
     notamment
    0.06
     домашних
    0.06
     Reservation
    0.06
    Activations Density 0.135%

    No Known Activations