© 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
    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. 15563
    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_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
     Hands
    -0.07
     overweight
    -0.07
    PickerController
    -0.07
     BL
    -0.06
    .is
    -0.06
     hysteria
    -0.06
    pawn
    -0.06
    broker
    -0.06
    ages
    -0.06
     Knee
    -0.06
    POSITIVE LOGITS
     whatsapp
    0.08
     apare
    0.07
     automatic
    0.07
     necessities
    0.06
     celebrations
    0.06
     найб
    0.06
    engkap
    0.06
    ameda
    0.06
     evitar
    0.06
     double
    0.06
    Activations Density 0.007%

    No Known Activations