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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 6528
    Prev
    Next
    INDEX
    Explanations

    Self-reference

    np_max-act · gemini-2.0-flash

    The neuron is primarily detecting first- and second-person pronouns (e.g., “you,” “your,” “my,” “me”) that indicate self-reference or direct address.

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

    self-referential language, especially first- and second-person pronouns and possessives indicating personal identity or ownership.

    oai_token-act-pair · gpt-5Triggered 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
    meteor
    -0.07
    ком
    -0.07
    кор
    -0.07
    uyễn
    -0.06
    listing
    -0.06
    .toolbox
    -0.06
    latest
    -0.06
    belief
    -0.06
     cvs
    -0.06
    .lv
    -0.06
    POSITIVE LOGITS
    ruc
    0.07
    oric
    0.07
    cion
    0.06
     //----------------------------------------------------------------
    0.06
     configured
    0.06
    ieg
    0.06
     Gear
    0.06
    >.
    0.06
    ’i
    0.06
    _display
    0.06
    Activations Density 0.118%

    No Known Activations