© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RESID-POST-AA
    6. 24926
    Prev
    Next
    INDEX
    Explanations

    Events, courses, and programs

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    득
    -0.07
    ISH
    -0.07
    άζ
    -0.07
    credible
    -0.06
    ish
    -0.06
     prepar
    -0.06
     해
    -0.06
     talent
    -0.06
    ари
    -0.06
    >y
    -0.06
    POSITIVE LOGITS
     mutlak
    0.07
    .StackTrace
    0.07
     tehdy
    0.07
    τσι
    0.06
    Extras
    0.06
    (write
    0.06
    jed
    0.06
    meyen
    0.06
    (track
    0.06
    验证码
    0.06
    Activations Density 0.166%

    No Known Activations