© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 13640
    Prev
    Next
    INDEX
    Explanations

    Legal and police contexts

    np_max-act · gemini-2.0-flash

    The neuron fires strongly on tokens tied to legal or judicial contexts—words like judge, court, arrested, charged, hearing, bail, 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
     查看
    -0.07
    宏
    -0.06
    ="../
    -0.06
    ::::::::::::::
    -0.06
     Jun
    -0.06
     mužů
    -0.06
    .PrintWriter
    -0.06
     REQUIRED
    -0.06
     ACT
    -0.06
    Sending
    -0.06
    POSITIVE LOGITS
     intens
    0.07
    apeut
    0.06
    ,target
    0.06
     ori
    0.06
    .correct
    0.06
    .Enqueue
    0.06
     Buccaneers
    0.06
     anterior
    0.06
     Ticaret
    0.06
    _fre
    0.06
    Activations Density 0.015%

    No Known Activations