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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 127101
    Prev
    Next
    INDEX
    Explanations

    frequently

    np_max-act · gemini-2.0-flash

    This neuron detects terms and phrases about repeated or frequent use of data or information—i.e. “frequently used,” “used again,” and similar references to reuse or caching.

    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
     прис
    -0.07
    Gro
    -0.06
     най
    -0.06
    алом
    -0.06
    :pointer
    -0.06
    aro
    -0.06
    endar
    -0.06
    _iteration
    -0.06
    lparr
    -0.06
     NEGLIGENCE
    -0.06
    POSITIVE LOGITS
    953
    0.08
     Zones
    0.07
     zone
    0.07
     jap
    0.07
    -check
    0.06
    ٣
    0.06
     Praha
    0.06
    Lee
    0.06
    俗
    0.06
     Bailey
    0.06
    Activations Density 0.009%

    No Known Activations