© 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. 56416
    Prev
    Next
    INDEX
    Explanations

    t

    np_max-act · gemini-2.0-flash

    This neuron fires on the little “t” token in the abbreviation “wrt” (i.e. it’s looking for the “wrt” sequence).

    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
    &oacute
    -0.07
     territory
    -0.07
     ⇒
    -0.07
     ');↵↵
    -0.07
     booking
    -0.06
    dashboard
    -0.06
    Been
    -0.06
    ≥
    -0.06
     *)↵
    -0.06
     RU
    -0.06
    POSITIVE LOGITS
     системы
    0.07
    泥
    0.06
     IPAddress
    0.06
     grd
    0.06
     carpets
    0.06
    уществ
    0.06
    "name
    0.06
     وجود
    0.06
     ys
    0.06
    _Item
    0.06
    Activations Density 0.001%

    No Known Activations