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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 15-RESID-POST-AA
    6. 54276
    Prev
    Next
    INDEX
    Explanations

    Lighting and usage

    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
     rats
    -0.10
    cos
    -0.08
     cos
    -0.07
     tits
    -0.07
     electron
    -0.07
    _bus
    -0.07
     Goal
    -0.07
     organs
    -0.07
    diff
    -0.07
    (matrix
    -0.07
    POSITIVE LOGITS
    avery
    0.06
    atab
    0.06
    ежду
    0.06
     &___
    0.06
     허
    0.06
    /pr
    0.06
     lumber
    0.06
     Youth
    0.06
     postage
    0.06
     whitespace
    0.06
    Activations Density 0.161%

    No Known Activations