© 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 (Instruct)
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 120609
    Prev
    Next
    INDEX
    Explanations

    System

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    achts
    -0.07
    chts
    -0.07
     metav
    -0.06
    parity
    -0.06
    左右
    -0.06
    左
    -0.06
     więcej
    -0.06
    issan
    -0.06
     شورای
    -0.06
    ync
    -0.06
    POSITIVE LOGITS
     charts
    0.08
    /context
    0.07
    .Stream
    0.07
    -position
    0.07
    \F
    0.07
     Cumhuriyet
    0.06
    arma
    0.06
     employs
    0.06
    >*
    0.06
    :_
    0.06
    Activations Density 0.004%

    No Known Activations