© 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. 13975
    Prev
    Next
    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric ratio expressions (e.g. “1:5,” “1:2,” etc.), i.e. number-colon-number patterns.

    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
    Wilson
    -0.09
    260
    -0.07
     Ku
    -0.06
    DRV
    -0.06
    getY
    -0.06
    sound
    -0.06
    218
    -0.06
     fmt
    -0.06
     EXTI
    -0.06
    *time
    -0.06
    POSITIVE LOGITS
    Designed
    0.07
    (chalk
    0.06
     Searching
    0.06
     fotoğraf
    0.06
     Digit
    0.06
    `=
    0.06
     Dress
    0.06
     prest
    0.06
    lif
    0.06
     disdain
    0.06
    Activations Density 0.005%

    No Known Activations