Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 11-RESID-POST-AA
    6. 27317
    Prev
    Next
    INDEX
    Explanations

    Scientific methods sections

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cancer
    -0.08
    dat
    -0.07
    ulators
    -0.07
    lte
    -0.07
    direct
    -0.07
     bass
    -0.06
     bott
    -0.06
     wild
    -0.06
     want
    -0.06
    licht
    -0.06
    POSITIVE LOGITS
     стороны
    0.07
     rencontrer
    0.06
    ViewById
    0.06
     заболеваний
    0.06
     calidad
    0.06
     отвеч
    0.06
    Mathf
    0.06
    치
    0.06
    .services
    0.06
     $_[
    0.06
    Activations Density 0.002%

    No Known Activations