© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 55921
    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
     petition
    -0.07
     canoe
    -0.06
    =zeros
    -0.06
    :<
    -0.06
    Paul
    -0.06
    sk
    -0.06
     nửa
    -0.06
     drifted
    -0.06
     Peaks
    -0.06
     crc
    -0.06
    POSITIVE LOGITS
    nem
    0.07
    .caption
    0.07
     IBM
    0.07
     Necklace
    0.07
    Variant
    0.07
     getConnection
    0.07
     छ
    0.07
     suspended
    0.06
     rehabilit
    0.06
     werden
    0.06
    Activations Density 0.003%

    No Known Activations