Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 27-RESID-POST-AA
    6. 102092
    Prev
    Next
    INDEX
    Explanations

    rebuttals and responses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ampo
    -0.07
     Jordan
    -0.07
     risks
    -0.06
    .notice
    -0.06
     Nodo
    -0.06
    Islam
    -0.06
     알려
    -0.06
     tables
    -0.06
     Đây
    -0.06
    ेल
    -0.06
    POSITIVE LOGITS
    .instagram
    0.07
    .Migrations
    0.06
    InChildren
    0.06
    alsex
    0.06
    umbledore
    0.06
     avid
    0.06
    .usermodel
    0.06
    '&&
    0.06
     arab
    0.06
     userService
    0.06
    Activations Density 0.535%

    No Known Activations