© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 93526
    Prev
    Next
    INDEX
    Explanations

    People

    np_max-act · gemini-2.0-flash

    The neuron selectively responds to tokens that are parts of personal names (proper nouns).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    references to notable individuals and their achievements.

    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
     회원
    -0.07
     extraordinary
    -0.06
     sobie
    -0.06
     Você
    -0.06
     технолог
    -0.06
    йте
    -0.06
     än
    -0.06
    �
    -0.06
     vara
    -0.06
     downloader
    -0.06
    POSITIVE LOGITS
     Santa
    0.08
    chip
    0.07
    原始
    0.07
    ashington
    0.07
    Rectangle
    0.06
     Disabilities
    0.06
     parsed
    0.06
    ightly
    0.06
    licenses
    0.06
     heed
    0.06
    Activations Density 0.262%

    No Known Activations