© 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. 60194
    Prev
    Next
    INDEX
    Explanations

    Stack Exchange sites

    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
    timeofday
    -0.07
     Shape
    -0.07
     forest
    -0.07
     beverage
    -0.07
    .Scanner
    -0.07
    ffa
    -0.06
     افز
    -0.06
    Clark
    -0.06
    Ui
    -0.06
    fw
    -0.06
    POSITIVE LOGITS
    MYSQL
    0.07
     Mısır
    0.07
     "**
    0.06
    �
    0.06
    bird
    0.06
    'LBL
    0.05
     ['/
    0.05
    CurrentValue
    0.05
     Cair
    0.05
    Expires
    0.05
    Activations Density 0.013%

    No Known Activations