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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 19-RESID-POST-AA
    6. 118386
    Prev
    Next
    INDEX
    Explanations

    Names

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     domina
    -0.06
    wię
    -0.06
    meler
    -0.06
    道路
    -0.06
    ومی
    -0.06
    ibNameOrNil
    -0.06
    BOSE
    -0.06
    LEncoder
    -0.06
     année
    -0.06
    emplo
    -0.06
    POSITIVE LOGITS
     từ
    0.07
     EVP
    0.07
     compare
    0.07
     kol
    0.06
    _blk
    0.06
     suck
    0.06
    eing
    0.06
     separately
    0.06
     Convention
    0.06
     user
    0.06
    Activations Density 0.002%

    No Known Activations