© 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. 42555
    Prev
    Next
    INDEX
    Explanations

    Legal and criminal cases

    np_max-act · gemini-2.0-flash

    legal terminology related to formal proceedings.

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

    The neuron activates on Portuguese legal‐procedure jargon (e.g. terms like “prescrição,” “decadência,” “extinção,” “inciso,” “execução,” etc.).

    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
    iving
    -0.07
    /ext
    -0.07
     Spawn
    -0.06
     exponent
    -0.06
     اجر
    -0.06
    fish
    -0.06
    +N
    -0.06
    ukes
    -0.06
     应
    -0.06
     insightful
    -0.06
    POSITIVE LOGITS
    �細
    0.07
     Voters
    0.07
     GlobalKey
    0.06
     sóng
    0.06
     Gauss
    0.06
     pollut
    0.06
    RELATED
    0.06
    。“
    0.06
    γό
    0.06
     goodwill
    0.06
    Activations Density 0.054%

    No Known Activations