© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43514
    Prev
    Next
    INDEX
    Explanations

    ING

    np_max-act · gemini-2.0-flash

    The neuron is picking up document-header terms that label the procedural posture (e.g. “Original Proceeding,” “Memorandum Opinion,” “Relator,” 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
    ffe
    -0.07
    202
    -0.07
    /List
    -0.07
    ชนะ
    -0.06
     Counsel
    -0.06
    SOR
    -0.06
     Coun
    -0.06
     Patricia
    -0.06
     VA
    -0.06
     lawmaker
    -0.06
    POSITIVE LOGITS
    _ori
    0.07
     آسیاب
    0.06
    (jq
    0.06
    (isinstance
    0.06
     mongodb
    0.06
    .hasOwnProperty
    0.06
    ทะ
    0.06
    oài
    0.06
    .settings
    0.06
    ERİ
    0.06
    Activations Density 0.001%

    No Known Activations