© 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. 15-RESID-POST-AA
    6. 25499
    Prev
    Next
    INDEX
    Explanations

    punctuation marks

    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
    ��이터
    -0.07
     marca
    -0.07
     HDF
    -0.06
    으며
    -0.06
     Member
    -0.06
     multiples
    -0.06
     KW
    -0.06
     geared
    -0.06
    引用频次
    -0.06
     repo
    -0.06
    POSITIVE LOGITS
    spread
    0.07
    iến
    0.07
    maid
    0.07
     ${(
    0.06
    ể
    0.06
     QtWidgets
    0.06
    .main
    0.06
    asley
    0.06
    Throwable
    0.06
    <U
    0.06
    Activations Density 0.054%

    No Known Activations