© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 54060
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron fires on fragments of proper names for external libraries or modules (e.g. “thali,” “mirador,” “cloudi,” “kythe”).

    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
    líb
    -0.07
    良い
    -0.07
     CLLocation
    -0.07
     Stre
    -0.07
     آس
    -0.06
     jaký
    -0.06
    (Tag
    -0.06
     -‐
    -0.06
     تفس
    -0.06
     concussion
    -0.06
    POSITIVE LOGITS
    __(*
    0.08
    ΐ
    0.07
    ritt
    0.06
     ROS
    0.06
    .getLeft
    0.06
    -V
    0.06
     UserId
    0.06
    *n
    0.06
    HH
    0.06
    <p
    0.06
    Activations Density 0.052%

    No Known Activations