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. 123462
    Prev
    Next
    INDEX
    Explanations

    mistakes or errors

    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
    apeutic
    -0.07
     BU
    -0.06
    átu
    -0.06
    _combine
    -0.06
     brother
    -0.06
     Answers
    -0.06
    bate
    -0.06
    .sms
    -0.05
    .sam
    -0.05
     ทอง
    -0.05
    POSITIVE LOGITS
    Krist
    0.09
     Beatles
    0.07
    _pll
    0.07
     ARISING
    0.07
    -temp
    0.06
    $$$$
    0.06
     potrze
    0.06
    Acc
    0.06
    _puts
    0.06
     Aug
    0.06
    Activations Density 0.123%

    No Known Activations