© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 125980
    Prev
    Next
    INDEX
    Explanations

    quotation marks/parentheses

    np_max-act · gemini-2.0-flash

    The neuron is picking up decimal number literals (floating-point values) 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
     ___
    -0.07
    ))(
    -0.07
    мини
    -0.06
     IC
    -0.06
     withstand
    -0.06
    ContainerGap
    -0.06
    Orig
    -0.06
    :int
    -0.06
     submissions
    -0.06
     classNames
    -0.06
    POSITIVE LOGITS
    正确
    0.06
     quicker
    0.06
     possessing
    0.06
    ROADCAST
    0.06
     Nombre
    0.06
    innen
    0.06
    чні
    0.06
     النو
    0.06
     Looks
    0.06
    $result
    0.06
    Activations Density 0.015%

    No Known Activations