© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 76493
    Prev
    Next
    INDEX
    Explanations

    relationship/sexual situations

    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
    чини
    -0.07
    فت
    -0.07
    _idx
    -0.06
    _player
    -0.06
     Speedway
    -0.06
    าอย
    -0.06
     skiing
    -0.06
     önce
    -0.06
    ftar
    -0.06
     Har
    -0.06
    POSITIVE LOGITS
    stat
    0.08
    .ajax
    0.07
    .Model
    0.07
     indu
    0.07
    $res
    0.07
     Brasil
    0.07
     General
    0.07
     ]),↵
    0.07
     general
    0.06
    Urban
    0.06
    Activations Density 0.008%

    No Known Activations