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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 19-RESID-POST-AA
    6. 83761
    Prev
    Next
    INDEX
    Explanations

    ICPSR data/research

    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
    ACEMENT
    -0.06
    .findall
    -0.06
    -таки
    -0.06
     ();↵↵
    -0.06
     tween
    -0.06
     municipal
    -0.06
     postcode
    -0.06
    ulence
    -0.06
    etypes
    -0.06
    odka
    -0.06
    POSITIVE LOGITS
    (urls
    0.07
     дор
    0.06
     všem
    0.06
    -selector
    0.06
     Arms
    0.06
     memo
    0.06
    [K
    0.06
     Barb
    0.06
     prevState
    0.06
     arts
    0.06
    Activations Density 0.004%

    No Known Activations