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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 84593
    Prev
    Next
    INDEX
    Explanations

    time and events

    np_max-act · gemini-2.0-flash

    references to sports events and player performances.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on words and phrases that mark times or dates—temporal references like “last night,” “day,” “preseason,” “Sunday,” or “Friday.”

    oai_token-act-pair · o4-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
     Hills
    -0.07
     punished
    -0.06
    coef
    -0.06
     lower
    -0.06
     rigorous
    -0.06
     přibliž
    -0.06
    우스
    -0.06
    ata
    -0.06
     cover
    -0.06
     ConcurrentHashMap
    -0.06
    POSITIVE LOGITS
     역시
    0.08
     الذهاب
    0.07
     viagra
    0.07
     chiếc
    0.07
     thai
    0.06
    .ย
    0.06
    .Support
    0.06
     th�
    0.06
     Spy
    0.06
     تغ
    0.06
    Activations Density 0.043%

    No Known Activations