© 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 (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 79427
    Prev
    Next
    INDEX
    Explanations

    animal migration

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FR
    -0.07
    icos
    -0.06
    raně
    -0.06
    蘭
    -0.06
    MessageType
    -0.06
    emales
    -0.06
    dependent
    -0.06
     atrocities
    -0.06
     쪽지
    -0.06
    represent
    -0.06
    POSITIVE LOGITS
     Power
    0.06
     McD
    0.06
     power
    0.06
     힘
    0.06
     err
    0.06
     zkušen
    0.06
     giảng
    0.06
    ผล
    0.06
    .Reverse
    0.06
    :value
    0.06
    Activations Density 0.011%

    No Known Activations