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. 111048
    Prev
    Next
    INDEX
    Explanations

    non

    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
    �合
    -0.07
    baru
    -0.07
     aber
    -0.06
     beats
    -0.06
    �
    -0.06
     utmost
    -0.06
     ff
    -0.06
     fim
    -0.06
     Governors
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    dre
    0.06
    cr
    0.06
    PLEX
    0.06
    lname
    0.06
    iams
    0.06
     Printer
    0.06
    agent
    0.06
    .when
    0.06
    izz
    0.06
    ơ
    0.06
    Activations Density 0.000%

    No Known Activations