© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 59127
    Prev
    Next
    INDEX
    Explanations

    brackets and quotes

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric literals—especially decimal/floating-point numbers—in code or data.

    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
    ใช
    -0.07
    /dat
    -0.06
     coz
    -0.06
     CFR
    -0.06
    nan
    -0.06
    \Data
    -0.06
     notch
    -0.06
     ku
    -0.06
     annonce
    -0.06
     cosa
    -0.05
    POSITIVE LOGITS
     lengths
    0.07
    _Read
    0.07
     мо
    0.07
     قل
    0.06
     между
    0.06
    جموع
    0.06
     introdu
    0.06
    (Socket
    0.06
     Wanted
    0.06
     stock
    0.06
    Activations Density 0.052%

    No Known Activations