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. 21378
    Prev
    Next
    INDEX
    Explanations

    Code

    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
    ♀
    -0.07
     sono
    -0.06
    ATER
    -0.06
    .onPause
    -0.06
    络
    -0.06
     کاملا
    -0.06
    _record
    -0.06
     Elli
    -0.06
     sequencing
    -0.06
    Needed
    -0.06
    POSITIVE LOGITS
    fbe
    0.06
    describe
    0.06
     stars
    0.06
    spot
    0.06
     phải
    0.06
    ænd
    0.06
    clinical
    0.06
    osaic
    0.06
     CODE
    0.06
    垂
    0.06
    Activations Density 0.221%

    No Known Activations