Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 19758
    Prev
    Next
    INDEX
    Explanations

    censorship

    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
     htons
    -0.07
     storefront
    -0.07
    .Release
    -0.07
     socialism
    -0.06
     Brothers
    -0.06
    (grad
    -0.06
    problem
    -0.06
     usleep
    -0.06
     find
    -0.06
     mile
    -0.06
    POSITIVE LOGITS
     censorship
    0.13
     censor
    0.12
    ensored
    0.11
    COR
    0.07
    SER
    0.07
    δή
    0.07
    ورد
    0.06
    สะ
    0.06
     Ceiling
    0.06
    ussy
    0.06
    Activations Density 0.003%

    No Known Activations