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. 9918
    Prev
    Next
    INDEX
    Explanations

    the

    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
     purchaser
    -0.07
     barrel
    -0.07
     itching
    -0.06
    .BO
    -0.06
    AIL
    -0.06
    15
    -0.06
     pregnant
    -0.06
    ाज
    -0.06
    neck
    -0.06
    ноч
    -0.06
    POSITIVE LOGITS
     self
    0.06
     معل
    0.06
     投稿日
    0.06
     بسی
    0.06
     openness
    0.06
    isms
    0.06
     ممکن
    0.06
     ridiculously
    0.06
    .typ
    0.06
     अगर
    0.06
    Activations Density 0.007%

    No Known Activations