© 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. 91190
    Prev
    Next
    INDEX
    Explanations

    fellow

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of academic honors and distinctions (e.g. “Fellow,” “Prize,” “Award”).

    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
     boxes
    -0.06
    icester
    -0.06
     HK
    -0.06
    atar
    -0.06
    Mur
    -0.06
     أحمد
    -0.06
     alarmed
    -0.06
     bitmap
    -0.06
     sky
    -0.06
    Mad
    -0.06
    POSITIVE LOGITS
     fellowship
    0.11
     Fellowship
    0.11
     Fellow
    0.09
     Fell
    0.09
    ////////////////////////////////////////////////////////////////////
    0.08
    haps
    0.07
    .Patient
    0.07
    fell
    0.07
    ellow
    0.07
     Stevenson
    0.07
    Activations Density 0.002%

    No Known Activations