© 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. 109409
    Prev
    Next
    INDEX
    Explanations

    user-generated content

    np_max-act · gemini-2.0-flash

    The neuron fires on direct second-person address—especially the pronouns “you” and “your.”

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

    sentences that open a formal request or inquiry in first person (e.g., "I am writing to..." / "I would like to...").

    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
    -summary
    -0.07
     illustrations
    -0.06
     Programme
    -0.06
     lump
    -0.06
    Strip
    -0.06
    Colour
    -0.06
    禁止
    -0.06
    oval
    -0.06
    Depth
    -0.06
    face
    -0.06
    POSITIVE LOGITS
    _AURA
    0.07
    :::/
    0.07
    _nil
    0.06
    //
    0.06
    erule
    0.06
     زیرا
    0.06
    _cut
    0.06
    imesteps
    0.06
     perí
    0.06
     {{{
    0.06
    Activations Density 0.192%

    No Known Activations