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. 104148
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    court-related terms and actions involving legal proceedings and governmental authority.

    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
    조
    -0.07
     DIG
    -0.07
    _SUCCESS
    -0.07
     Certificate
    -0.06
     Accuracy
    -0.06
     Rae
    -0.06
    арів
    -0.06
    Spo
    -0.06
     Evans
    -0.06
     continual
    -0.06
    POSITIVE LOGITS
     соблюд
    0.06
    "use
    0.06
     bag
    0.06
    ріп
    0.06
    ص
    0.06
    지가
    0.06
    %).↵↵
    0.06
    ']?></
    0.06
    (toolbar
    0.06
     genel
    0.06
    Activations Density 0.022%

    No Known Activations