© 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. 92228
    Prev
    Next
    INDEX
    Explanations

    were

    np_max-act · gemini-2.0-flash

    The neuron fires on content words in biographical or career‐history sentences—i.e. tokens that appear in factual descriptions of people’s roles, activities, and life events.

    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
     Vaults
    -0.06
    \xf
    -0.06
     веч
    -0.06
     Louis
    -0.06
    овать
    -0.06
    _FOLLOW
    -0.06
     Harley
    -0.06
     jogging
    -0.06
     Andre
    -0.06
    お
    -0.05
    POSITIVE LOGITS
    Debug
    0.06
    éf
    0.06
    ilyn
    0.06
     Enables
    0.06
     yum
    0.06
     základní
    0.06
    toInt
    0.06
     postpon
    0.06
    uble
    0.06
     traj
    0.06
    Activations Density 0.259%

    No Known Activations