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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 16186
    Prev
    Next
    INDEX
    Explanations

    Quotation marks

    np_max-act · gemini-2.0-flash

    This neuron activates on floating-point number literals (decimal numbers) in the text.

    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
     بهره
    -0.07
    pal
    -0.07
     Bai
    -0.06
    	grid
    -0.06
     implant
    -0.06
     getInt
    -0.06
    SSID
    -0.06
    those
    -0.06
     those
    -0.06
     clip
    -0.06
    POSITIVE LOGITS
     піш
    0.07
    -strokes
    0.06
    /weather
    0.06
     hled
    0.06
     '>
    0.06
    濃
    0.06
    [g
    0.06
    ظمة
    0.06
    \Form
    0.06
    <stdio
    0.06
    Activations Density 0.012%

    No Known Activations