© 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. 126978
    Prev
    Next
    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash

    The neuron activates on words used to attribute or credit sponsors and presenters (e.g. “by,” “presented,” “sponsored,” “made possible by,” 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
    School
    -0.07
     již
    -0.07
    Processor
    -0.07
     fibre
    -0.07
     şehir
    -0.07
    rowser
    -0.06
     exploration
    -0.06
     innocent
    -0.06
    .bottom
    -0.06
    everyone
    -0.06
    POSITIVE LOGITS
    typeparam
    0.07
     م
    0.07
     plc
    0.06
    Ư
    0.06
    .ibm
    0.06
    StatusLabel
    0.06
     PLC
    0.06
    ALI
    0.06
    "<?
    0.06
     iht
    0.06
    Activations Density 0.008%

    No Known Activations