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. 23-RESID-POST-AA
    6. 40661
    Prev
    Next
    INDEX
    Explanations

    success

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Levels
    -0.07
    ulant
    -0.06
     kapı
    -0.06
     Rat
    -0.06
    Combine
    -0.06
    table
    -0.06
     bryster
    -0.06
    setLayout
    -0.06
     ure
    -0.06
     admirable
    -0.06
    POSITIVE LOGITS
    Optional
    0.07
    enc
    0.07
     News
    0.07
     hopes
    0.07
     �
    0.07
     emergencies
    0.07
    115
    0.06
     Origin
    0.06
    .ss
    0.06
    ΕΣ
    0.06
    Activations Density 0.018%

    No Known Activations