© 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
    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. 129869
    Prev
    Next
    INDEX
    Explanations

    academic

    np_max-act · gemini-2.0-flash

    The neuron is tuned to spot mentions of academic credentials and achievements (e.g. majors, GPAs, honor rolls) in athlete profiles.

    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
     Rosen
    -0.06
    gis
    -0.06
     ple
    -0.06
     ít
    -0.06
    _simple
    -0.06
     Dar
    -0.06
    ampire
    -0.06
     relational
    -0.06
    .yang
    -0.06
     rob
    -0.06
    POSITIVE LOGITS
    317
    0.07
     Prior
    0.07
     vowel
    0.07
    	print
    0.06
    .environment
    0.06
     انسان
    0.06
         ↵↵
    0.06
     paddle
    0.06
    .Program
    0.06
     secre
    0.06
    Activations Density 0.006%

    No Known Activations