© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 53630
    Prev
    Next
    INDEX
    Explanations

    Switzerland

    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
     Cher
    -0.06
     Capitals
    -0.06
    setContent
    -0.06
    Προ
    -0.06
    爭
    -0.06
     anlat
    -0.06
     dealings
    -0.06
    ,model
    -0.06
    ади
    -0.06
     wx
    -0.06
    POSITIVE LOGITS
     телеф
    0.06
    대학교
    0.06
    asil
    0.06
    IPPING
    0.06
    舰
    0.06
     *)"
    0.06
     rates
    0.06
    env
    0.06
     Machines
    0.06
    advert
    0.06
    Activations Density 0.074%

    No Known Activations