© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 89829
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    This neuron fires on header and metadata elements in legal opinions (e.g. party or lawyer names, court identifiers, dates, memorandum/order headings, and related case‐citation tokens).

    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
    _route
    -0.07
    _corner
    -0.07
     lump
    -0.07
     MTV
    -0.07
     invaders
    -0.07
    ella
    -0.07
    achi
    -0.06
     compar
    -0.06
    -svg
    -0.06
     coronary
    -0.06
    POSITIVE LOGITS
    oningen
    0.06
     Vermont
    0.06
     viewHolder
    0.06
    eload
    0.06
    .hero
    0.06
    โจ
    0.06
    减
    0.06
    foreign
    0.06
    ποιη
    0.05
    ;amp
    0.05
    Activations Density 0.011%

    No Known Activations