© 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. 128688
    Prev
    Next
    INDEX
    Explanations

    law office

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of law firms or attorneys’ offices (e.g., “Law Office,” “Law Firm,” and similar counsel listings).

    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
    Cs
    -0.07
     favourable
    -0.07
    _written
    -0.07
    _cube
    -0.06
     box
    -0.06
    _BROWSER
    -0.06
    Mary
    -0.06
     feet
    -0.06
     adultery
    -0.06
     radio
    -0.06
    POSITIVE LOGITS
    пеки
    0.08
    .addField
    0.07
     모르
    0.07
     chờ
    0.07
     somew
    0.07
    .DataFrame
    0.07
    StartupScript
    0.07
     весь
    0.06
     либо
    0.06
    AGEMENT
    0.06
    Activations Density 0.014%

    No Known Activations