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. 54182
    Prev
    Next
    INDEX
    Explanations

    monolayers

    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
     박
    -0.07
    /B
    -0.06
    Wrong
    -0.06
     valley
    -0.06
     MutableList
    -0.06
    /N
    -0.06
    iri
    -0.06
     '.'
    -0.06
    oru
    -0.06
     amo
    -0.06
    POSITIVE LOGITS
     resonance
    0.06
    .Connect
    0.06
    userinfo
    0.06
    říz
    0.06
     Cran
    0.06
    _accel
    0.06
     ListBox
    0.06
     Соб
    0.06
    濟
    0.06
                   ↵
    0.06
    Activations Density 0.037%

    No Known Activations