© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 58124
    Prev
    Next
    INDEX
    Explanations

    null

    np_max-act · gemini-2.0-flash

    The neuron is primarily spotting floating‐point numeric literals (tokens containing a decimal point).

    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
     Standards
    -0.06
     شد
    -0.06
     osob
    -0.06
    ène
    -0.06
     VIA
    -0.06
    (Util
    -0.06
     +(
    -0.06
     suicide
    -0.06
    <b
    -0.06
     standards
    -0.05
    POSITIVE LOGITS
     brewed
    0.07
    getDate
    0.07
    gold
    0.06
    ड़
    0.06
     puis
    0.06
    ussen
    0.06
    .s
    0.06
     مستق
    0.06
    .TR
    0.06
     Goddess
    0.06
    Activations Density 0.009%

    No Known Activations