© 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. 56005
    Prev
    Next
    INDEX
    Explanations

    In

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens—years, dates, and other numerical values (e.g., census figures, measurements).

    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
    เจร
    -0.07
    sl
    -0.07
    FTER
    -0.07
    330
    -0.06
    urança
    -0.06
     관계
    -0.06
    imizin
    -0.06
    éra
    -0.06
     �
    -0.06
     Steph
    -0.06
    POSITIVE LOGITS
     geschichten
    0.06
    xffff
    0.06
    $output
    0.06
    =random
    0.06
    @foreach
    0.06
     '%$
    0.06
     دين
    0.06
     аб
    0.06
    。\
    0.05
    (cam
    0.05
    Activations Density 0.039%

    No Known Activations