© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 17628
    Prev
    Next
    INDEX
    Explanations

    "I am"

    np_max-act · gemini-2.0-flash

    contractions with 'm (I'm, we're).

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @chuloivawork
    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
     hiatus
    -0.07
    ázky
    -0.07
    .abspath
    -0.07
     fields
    -0.07
    "C
    -0.07
    insula
    -0.06
     credited
    -0.06
     xr
    -0.06
    hof
    -0.06
    _ro
    -0.06
    POSITIVE LOGITS
     SHIPPING
    0.08
     Fest
    0.07
     Senior
    0.06
    بيع
    0.06
    oader
    0.06
    زاده
    0.06
    hind
    0.06
    /lang
    0.06
     TAM
    0.06
    	placeholder
    0.06
    Activations Density 0.038%

    No Known Activations