© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 13750
    Prev
    Next
    INDEX
    Explanations

    /net

    np_max-act · gemini-2.0-flash

    The neuron fires on the numeric version identifiers (e.g. 4.0859375, 4.078125, etc.) in import paths, i.e. it detects floating-point version numbers.

    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
     newX
    -0.06
    Spark
    -0.06
    -mediated
    -0.06
    _cons
    -0.06
    GPL
    -0.06
    arefa
    -0.06
    剛
    -0.06
    _BL
    -0.06
    RenderWindow
    -0.06
     gcd
    -0.06
    POSITIVE LOGITS
     Kentucky
    0.07
    	iVar
    0.06
     chiến
    0.06
     перепис
    0.06
     ///</
    0.06
    ,//
    0.06
    .Debug
    0.06
    мотря
    0.06
    ranges
    0.06
     cookie
    0.06
    Activations Density 0.000%

    No Known Activations