© 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. 88911
    Prev
    Next
    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash

    This neuron detects date components (especially the month/day parts) in the document headers.

    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
     películ
    -0.06
     Paleo
    -0.06
    変更
    -0.06
     uncont
    -0.06
    иров
    -0.06
    .trip
    -0.06
    Ast
    -0.06
     clinicians
    -0.05
     medically
    -0.05
     تولید
    -0.05
    POSITIVE LOGITS
     preach
    0.07
    结构
    0.07
     extraordinarily
    0.07
     VB
    0.07
    normalized
    0.07
    (sb
    0.06
     Crane
    0.06
    <pre
    0.06
     grateful
    0.06
    /avatar
    0.06
    Activations Density 0.004%

    No Known Activations