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. 130517
    Prev
    Next
    INDEX
    Explanations

    aw

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the word “law.”

    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
    .FlatAppearance
    -0.08
    Persist
    -0.07
    allenges
    -0.07
     Gü
    -0.07
     �
    -0.06
    ��
    -0.06
     CIS
    -0.06
    Indeed
    -0.06
    aming
    -0.06
    酒
    -0.06
    POSITIVE LOGITS
     governed
    0.07
    gett
    0.06
         ↵↵
    0.06
    -definition
    0.06
    /lab
    0.06
    ;}
    0.06
     shri
    0.06
     backward
    0.06
     những
    0.06
    ваются
    0.05
    Activations Density 0.001%

    No Known Activations