© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 127109
    Prev
    Next
    INDEX
    Explanations

    communicate

    np_max-act · gemini-2.0-flash

    The neuron fires on words referring to the act of sending or transferring information (e.g. “communicate,” “communication,” “transmit,” “transmission,” 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
     Knowledge
    -0.06
     Compet
    -0.06
    (member
    -0.06
    Translator
    -0.06
     Ak
    -0.06
     {{↵
    -0.06
    -cross
    -0.06
     eternal
    -0.06
     trouve
    -0.06
    -Russian
    -0.06
    POSITIVE LOGITS
     setUp
    0.07
     karş
    0.06
     formatDate
    0.06
    <\/
    0.06
     kvinner
    0.06
    /octet
    0.06
     INSTALL
    0.06
    /**<
    0.06
     üretim
    0.06
    \HttpFoundation
    0.06
    Activations Density 0.013%

    No Known Activations