© 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. 6176
    Prev
    Next
    INDEX
    Explanations

    new

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on numeric tokens—especially floating-point or decimal numbers—highlighting when the text contains technical numeric values.

    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
     حکومت
    -0.07
     turns
    -0.07
    英语
    -0.07
     launches
    -0.07
     Trang
    -0.07
     Blowjob
    -0.06
     upbringing
    -0.06
    	x
    -0.06
     prec
    -0.06
    ово
    -0.06
    POSITIVE LOGITS
     نی
    0.07
    收益
    0.07
    ユ
    0.06
     mobil
    0.06
    ügen
    0.06
    avec
    0.06
    unya
    0.06
    [--
    0.06
    ｨ
    0.06
    due
    0.06
    Activations Density 0.027%

    No Known Activations