© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 72680
    Prev
    Next
    INDEX
    Explanations

    hiring/qualifications/affirmative action

    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
    685
    -0.07
     ENV
    -0.06
     트
    -0.06
    (UnityEngine
    -0.06
     طل
    -0.06
     Commands
    -0.06
     subconscious
    -0.06
    .system
    -0.06
     Manufacturers
    -0.06
    107
    -0.06
    POSITIVE LOGITS
    卒
    0.07
     зуп
    0.07
     isVisible
    0.07
     možné
    0.07
    лся
    0.07
    ใกล
    0.07
    Ⅵ
    0.07
    ?]
    0.07
     ora
    0.07
     otra
    0.06
    Activations Density 0.015%

    No Known Activations