© 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. 57737
    Prev
    Next
    INDEX
    Explanations

    than

    np_max-act · gemini-2.0-flash

    The neuron detects numeric and schedule-related tokens—dates, times, counts, and other numerals.

    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
    Rows
    -0.08
    _FOREACH
    -0.07
     legendary
    -0.07
    チェ
    -0.06
     صور
    -0.06
    .credentials
    -0.06
     recipients
    -0.06
    یر
    -0.06
     senin
    -0.06
    aming
    -0.06
    POSITIVE LOGITS
    	bit
    0.07
     прий
    0.07
    /data
    0.07
     ввод
    0.06
    Interested
    0.06
     QModelIndex
    0.06
     ave
    0.06
     Angular
    0.06
    -box
    0.06
    Pub
    0.06
    Activations Density 0.007%

    No Known Activations