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. 11-RESID-POST-AA
    6. 24112
    Prev
    Next
    INDEX
    Explanations

    resin

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .pitch
    -0.07
     Kamp
    -0.06
     traumatic
    -0.06
     live
    -0.06
    Placement
    -0.06
    .Globalization
    -0.06
    .true
    -0.06
    you
    -0.06
    熟
    -0.06
    になって
    -0.06
    POSITIVE LOGITS
     resin
    0.12
    sin
    0.08
    in
    0.08
     Sin
    0.08
    IN
    0.08
    .FindAsync
    0.08
    mesine
    0.07
    S
    0.07
    tin
    0.07
     sin
    0.07
    Activations Density 0.003%

    No Known Activations