© 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. 44442
    Prev
    Next
    INDEX
    Explanations

    personal pronouns

    np_max-act · gemini-2.0-flash

    The neuron detects first-person personal-pronoun references (“I,” “my,” “you,” “’m,” etc.) in numerical age-calculation contexts.

    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
     civil
    -0.07
    (unit
    -0.07
     deputy
    -0.07
     deliver
    -0.06
    LEMENT
    -0.06
    istrat
    -0.06
     vandal
    -0.06
    -campus
    -0.06
     Exxon
    -0.06
     vampires
    -0.06
    POSITIVE LOGITS
    ='',
    0.07
     औ
    0.06
     우
    0.06
    目を
    0.06
     خم
    0.06
     pp
    0.06
    行为
    0.06
     beforeSend
    0.06
    .updateDynamic
    0.06
     khu
    0.06
    Activations Density 0.007%

    No Known Activations