© 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. 43114
    Prev
    Next
    INDEX
    Explanations

    article "a" or "an"

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens that represent decimal fractions (floating‐point 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
    ]:
↵
    -0.07
    anus
    -0.06
    .DEFINE
    -0.06
    ]){
    -0.06
    ி
    -0.06
     blanket
    -0.06
     yalnızca
    -0.06
    ptal
    -0.06
    کز
    -0.06
     умови
    -0.06
    POSITIVE LOGITS
     Marker
    0.06
     raster
    0.06
    준
    0.06
    ……」↵↵
    0.06
     Convenience
    0.06
     �
    0.06
    	IN
    0.06
    /android
    0.06
    lifting
    0.05
     irresistible
    0.05
    Activations Density 0.017%

    No Known Activations