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. 15-RESID-POST-AA
    6. 27741
    Prev
    Next
    INDEX
    Explanations

    soluble

    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
     superstar
    -0.07
    yards
    -0.06
     Yard
    -0.06
    destination
    -0.06
    288
    -0.06
     concessions
    -0.06
     yards
    -0.06
     yard
    -0.06
    直
    -0.06
    скую
    -0.06
    POSITIVE LOGITS
    wallet
    0.07
    \Web
    0.07
    жно
    0.07
    uble
    0.07
     throm
    0.06
     ABI
    0.06
    userRepository
    0.06
    нт
    0.06
    Codec
    0.06
     p
    0.06
    Activations Density 0.010%

    No Known Activations