© 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. 129969
    Prev
    Next
    INDEX
    Explanations

    are, of

    np_max-act · gemini-2.0-flash

    The neuron fires on words and phrases expressing numeric quantities and fractions (e.g. “half,” “one fourth,” “third,” and related numbers) in math‐word‐problem contexts.

    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
    marine
    -0.06
    Nom
    -0.06
    	cnt
    -0.06
     paternal
    -0.06
     Liên
    -0.06
    pios
    -0.06
     ifstream
    -0.06
     Indicates
    -0.06
     EACH
    -0.06
    weight
    -0.06
    POSITIVE LOGITS
     ألف
    0.07
    olleyError
    0.07
    sey
    0.06
     práce
    0.06
     Techn
    0.06
    Registers
    0.06
    _typeDefinitionSize
    0.06
    "profile
    0.06
    مز
    0.06
     distinguish
    0.06
    Activations Density 0.017%

    No Known Activations