© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 87559
    Prev
    Next
    INDEX
    Explanations

    still going strong

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hasClass
    -0.07
    encia
    -0.07
    currentUser
    -0.07
    .EntityFrameworkCore
    -0.06
     Bài
    -0.06
     maxLength
    -0.06
    哪
    -0.06
    .removeClass
    -0.06
    ـل
    -0.06
    .YELLOW
    -0.06
    POSITIVE LOGITS
     mosque
    0.07
     oficial
    0.07
     ⌒
    0.07
     Meer
    0.06
    ETHOD
    0.06
    保
    0.06
    ,T
    0.06
    そう
    0.06
     phy
    0.06
    _BC
    0.06
    Activations Density 0.060%

    No Known Activations