© 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 (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 22924
    Prev
    Next
    INDEX
    Explanations

    Comma

    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
     建
    -0.07
    ين
    -0.07
    在地
    -0.07
    \Order
    -0.07
    .get
    -0.07
    .strict
    -0.07
     щ
    -0.07
     위치
    -0.07
    commended
    -0.06
    veyor
    -0.06
    POSITIVE LOGITS
     inex
    0.06
     disrupting
    0.06
     moderate
    0.06
     turquoise
    0.06
     дав
    0.05
     componentDidUpdate
    0.05
     قرآن
    0.05
     użytk
    0.05
    ckeditor
    0.05
     x
    0.05
    Activations Density 0.214%

    No Known Activations