© 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. 93979
    Prev
    Next
    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash

    programming-related syntax and code snippets.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron primarily detects personal pronouns (like “I,” “you,” etc.) indicating first‐ or second‐person references.

    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
    Number
    -0.06
    Flying
    -0.06
    _dbg
    -0.06
    	real
    -0.06
     Function
    -0.06
     Initialise
    -0.06
    637
    -0.06
    _speed
    -0.06
    ८
    -0.06
     tempo
    -0.06
    POSITIVE LOGITS
     I
    0.11
     we
    0.10
     you
    0.10
    —I
    0.09
     us
    0.08
    …I
    0.08
     they
    0.08
     she
    0.08
    -I
    0.08
     he
    0.08
    Activations Density 0.075%

    No Known Activations