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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 80899
    Prev
    Next
    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash

    legal terminology and keywords related to court cases and legal proceedings.

    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
    Principal
    -0.07
     Silk
    -0.06
     Hacker
    -0.06
    Exam
    -0.06
     із
    -0.06
     Pool
    -0.06
     Mongolia
    -0.06
     Mix
    -0.06
    ısında
    -0.06
    cut
    -0.06
    POSITIVE LOGITS
     předch
    0.07
     discovery
    0.06
     tanto
    0.06
    افته
    0.06
    الإنجليزية
    0.06
     předpok
    0.06
    (em
    0.06
     hemen
    0.06
     през
    0.06
    ][
    0.06
    Activations Density 0.018%

    No Known Activations