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. 3-RESID-POST-AA
    6. 94505
    Prev
    Next
    INDEX
    Explanations

    É

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (tensor
    -0.07
    默
    -0.06
    جان
    -0.06
    >x
    -0.06
     iş
    -0.06
    (direction
    -0.06
     전화
    -0.06
    .length
    -0.06
    Density
    -0.06
    ounder
    -0.06
    POSITIVE LOGITS
     É
    0.16
    É
    0.07
     responsibilities
    0.07
     ґ
    0.07
     intercept
    0.06
    Directories
    0.06
     steroid
    0.06
     scholarship
    0.06
     triangle
    0.06
     плен
    0.06
    Activations Density 0.006%

    No Known Activations