Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 105075
    Prev
    Next
    INDEX
    Explanations

    blog posts

    np_max-act · gemini-2.0-flash

    questions asking about someone's favorite or preferred thing (e.g., "favorite", "好きな", with items like color/food).

    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
    venture
    -0.07
     licenses
    -0.07
    .size
    -0.07
     dreams
    -0.06
    측
    -0.06
    ад
    -0.06
    欧
    -0.06
    yper
    -0.06
     predictor
    -0.06
    ewing
    -0.06
    POSITIVE LOGITS
    .HORIZONTAL
    0.07
    Textbox
    0.07
    >
    ↵
    ↵
    ↵
    0.07
     Tex
    0.07
     Knicks
    0.07
    Carousel
    0.06
     XHTML
    0.06
     Onun
    0.06
     Gemini
    0.06
    .Drawable
    0.06
    Activations Density 0.081%

    No Known Activations