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. 40495
    Prev
    Next
    INDEX
    Explanations

    section or article

    np_max-act · gemini-2.0-flash

    legal terminology related to court proceedings and decisions.

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

    This neuron fires on legal provision citations—references to constitutional articles or statutory sections (e.g. “Article II, Section 24”).

    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
     imkan
    -0.06
    _PEER
    -0.06
    .unit
    -0.06
     Kw
    -0.06
     unfavor
    -0.06
    Bush
    -0.06
    IPAddress
    -0.06
    布
    -0.06
    pawn
    -0.06
     Shan
    -0.06
    POSITIVE LOGITS
    ril
    0.07
    ','$
    0.06
     prohibit
    0.06
    ЎыџN
    0.06
    �
    0.06
     Mormon
    0.06
    دواج
    0.06
     пло
    0.06
     standoff
    0.06
     userid
    0.06
    Activations Density 0.005%

    No Known Activations