© 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. 11-RESID-POST-AA
    6. 52153
    Prev
    Next
    INDEX
    Explanations

    product descriptions

    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
    وو
    -0.07
     homophobic
    -0.06
     эффек
    -0.06
     genomes
    -0.06
     fichier
    -0.06
     Chemistry
    -0.06
    .isfile
    -0.06
     표시
    -0.06
     fridge
    -0.06
    '}).
    -0.06
    POSITIVE LOGITS
    .Bean
    0.07
    Enumeration
    0.07
    .asm
    0.07
    nám
    0.06
    AGE
    0.06
    Death
    0.06
    Art
    0.06
    PJ
    0.06
     Imagine
    0.06
    orer
    0.06
    Activations Density 0.058%

    No Known Activations