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. 83450
    Prev
    Next
    INDEX
    Explanations

    '

    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
    Bow
    -0.07
    orque
    -0.06
    sin
    -0.06
     lacking
    -0.06
    _jump
    -0.06
    horizontal
    -0.06
    easy
    -0.06
    ้ไข
    -0.06
    但
    -0.06
     Medic
    -0.06
    POSITIVE LOGITS
    PATH
    0.07
    (integer
    0.07
    平台
    0.07
     Nest
    0.07
     провед
    0.07
     сосед
    0.06
     PageInfo
    0.06
     Vì
    0.06
    Streamer
    0.06
     강남
    0.06
    Activations Density 0.001%

    No Known Activations