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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 125262
    Prev
    Next
    INDEX
    Explanations

    under

    np_max-act · gemini-2.0-flash

    The neuron fires on phrases in license headers (e.g., “Licensed under the Apache License, Version 2.0”).

    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
     Unt
    -0.08
     Provincial
    -0.07
    _solver
    -0.07
    PILE
    -0.07
     selbst
    -0.07
    .jms
    -0.06
     все
    -0.06
     uh
    -0.06
    athlete
    -0.06
    mb
    -0.06
    POSITIVE LOGITS
    :red
    0.06
     النه
    0.06
    	store
    0.06
     навч
    0.06
     سلس
    0.06
    dataTable
    0.06
     المش
    0.06
    .xml
    0.06
     poo
    0.06
    (eventName
    0.06
    Activations Density 0.006%

    No Known Activations