© 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
    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. 6375
    Prev
    Next
    INDEX
    Explanations

    Personal pronouns

    np_max-act · gemini-2.0-flash

    This neuron detects first-person self-references (e.g. “I,” “me,” “my,” “mine”).

    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
    ucch
    -0.07
    onium
    -0.07
     sector
    -0.06
    _SYNC
    -0.06
     characters
    -0.06
    zee
    -0.06
     Align
    -0.06
    acters
    -0.06
    asket
    -0.06
     Extraction
    -0.06
    POSITIVE LOGITS
     Vari
    0.07
    (MethodImplOptions
    0.06
    (commit
    0.06
    Если
    0.06
    .FormattingEnabled
    0.06
     спіл
    0.06
     &(
    0.06
    .ModelForm
    0.06
    .filePath
    0.06
     نام
    0.06
    Activations Density 0.139%

    No Known Activations