© 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. 60306
    Prev
    Next
    INDEX
    Explanations

    agreement or emphasis

    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
    constructor
    -0.06
    _tuple
    -0.06
    ="'.
    -0.06
    寿
    -0.06
    Appointment
    -0.06
    ;")↵
    -0.06
    ня
    -0.06
    HEME
    -0.06
    Pocket
    -0.06
    //{↵
    -0.06
    POSITIVE LOGITS
    νει
    0.07
    /A
    0.07
    larg
    0.06
     Af
    0.06
     crack
    0.06
     Ary
    0.06
     ACM
    0.06
     ＼
    0.06
    Insensitive
    0.06
    yyval
    0.06
    Activations Density 0.052%

    No Known Activations