© 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
    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. 73981
    Prev
    Next
    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash

    phrases related to identity and personal experiences with cultural or societal commentary.

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

    This neuron detects French-language words or phrases.

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

    Instances of first-person self-reference (first-person pronouns like "I" or "je") indicating the speaker referring to themselves.

    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
     you
    -0.10
     You
    -0.09
     Their
    -0.09
     your
    -0.08
     their
    -0.08
     they
    -0.08
    You
    -0.08
    their
    -0.08
     They
    -0.07
     them
    -0.07
    POSITIVE LOGITS
     dikke
    0.08
     đạt
    0.07
     перест
    0.07
     bruises
    0.07
    启动
    0.07
     upsetting
    0.06
     добавить
    0.06
     hunger
    0.06
     Burada
    0.06
    zahl
    0.06
    Activations Density 0.734%

    No Known Activations