© 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. 57934
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    The neuron detects numeric expressions and quantitative data (e.g. numbers, percentages, and measurements).

    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
     eggs
    -0.07
     Beard
    -0.07
     getPage
    -0.06
     sequences
    -0.06
    otic
    -0.06
     helmet
    -0.06
     feed
    -0.06
    _dns
    -0.06
     encode
    -0.06
    verter
    -0.06
    POSITIVE LOGITS
     تصم
    0.07
    стве
    0.06
    ály
    0.06
     vừa
    0.06
     runaway
    0.06
    ardo
    0.06
    하였다
    0.06
    elop
    0.06
     scripture
    0.06
    Cla
    0.06
    Activations Density 0.225%

    No Known Activations