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. 55318
    Prev
    Next
    INDEX
    Explanations

    ViewBag

    np_max-act · gemini-2.0-flash

    phrases related to programming concepts, particularly in the context of web development.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects floating‐point numeric literals (decimal numbers) in code.

    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
    ารณ
    -0.07
     mesmer
    -0.07
     rusty
    -0.06
     Space
    -0.06
     chant
    -0.06
     chanting
    -0.06
    _unc
    -0.06
     datatype
    -0.06
     silver
    -0.06
    expectException
    -0.06
    POSITIVE LOGITS
     ViewBag
    0.09
    باح
    0.07
     skyline
    0.07
     Vog
    0.07
     Emit
    0.06
    RODUCTION
    0.06
    (begin
    0.06
    .Lines
    0.06
    	gtk
    0.06
    .move
    0.06
    Activations Density 0.001%

    No Known Activations