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. 53239
    Prev
    Next
    INDEX
    Explanations

    html/xml tags

    np_max-act · gemini-2.0-flash

    phrases that discuss actions involving people and their roles or capabilities.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    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
    心里
    -0.06
    _death
    -0.06
    -cigarettes
    -0.06
    體
    -0.06
     Pé
    -0.06
    ωσε
    -0.06
    rist
    -0.06
     Dixon
    -0.06
    ์ด
    -0.06
    -five
    -0.06
    POSITIVE LOGITS
    sburgh
    0.07
    .setTo
    0.07
    чим
    0.07
     abandoning
    0.06
    chron
    0.06
     Bylo
    0.06
     مسیر
    0.06
     ORDER
    0.06
    axon
    0.06
     ý
    0.06
    Activations Density 0.001%

    No Known Activations