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. 15-RESID-POST-AA
    6. 92992
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    数据库
    -0.07
     Πολ
    -0.07
    (print
    -0.07
     Bolton
    -0.06
    computer
    -0.06
    (identity
    -0.06
    oper
    -0.06
    .serialize
    -0.06
    owitz
    -0.06
    landır
    -0.06
    POSITIVE LOGITS
     Loved
    0.06
     contre
    0.06
     apresent
    0.06
     Movement
    0.06
     unre
    0.06
    eventName
    0.06
     entert
    0.06
     éc
    0.06
     Hearth
    0.06
     haven
    0.06
    Activations Density 0.098%

    No Known Activations