© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 58285
    Prev
    Next
    INDEX
    Explanations

    first-person

    np_max-act · gemini-2.0-flash

    The neuron primarily detects first-person references—tokens like “I,” “my,” etc., in user statements.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    sentences where the author speaks in first person to describe a problem, action, or experience.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
     sacrificing
    -0.06
     lst
    -0.06
    ceiving
    -0.06
    관
    -0.06
     DAO
    -0.06
    _LOOP
    -0.06
     Fay
    -0.06
    Iran
    -0.06
     BitSet
    -0.06
     Shapiro
    -0.06
    POSITIVE LOGITS
    _eval
    0.07
    ίκη
    0.07
    ounding
    0.06
     GetValue
    0.06
    eldo
    0.06
    'ils
    0.06
    IsUnicode
    0.06
    -native
    0.06
    ibr
    0.06
    @\
    0.06
    Activations Density 0.182%

    No Known Activations