© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RESID-POST-AA
    11. 93994
    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
     له
    -0.08
     maid
    -0.07
     꿈
    -0.07
     incub
    -0.07
     caf
    -0.07
     rabbit
    -0.06
     Reflex
    -0.06
     cords
    -0.06
     ()
    -0.06
    _INF
    -0.06
    POSITIVE LOGITS
    cia
    0.07
    러리
    0.07
     nearby
    0.07
    .getCurrentUser
    0.06
    (JSONObject
    0.06
    .RightToLeft
    0.06
    <Model
    0.06
    >This
    0.06
     reign
    0.06
    (which
    0.06
    Activations Density 0.008%

    No Known Activations