© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 13931
    Prev
    Next
    INDEX
    Explanations

    length or runtime

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric metadata values (e.g. lengths, runtimes, durations, ratings) in document metadata fields.

    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
     hug
    -0.07
     orchest
    -0.07
     podr
    -0.07
     Jed
    -0.07
     buttonWithType
    -0.07
    っている
    -0.07
     현대
    -0.07
    达到
    -0.06
     chữa
    -0.06
     çalışmaları
    -0.06
    POSITIVE LOGITS
     حتى
    0.07
    redit
    0.06
     clearer
    0.06
    NO
    0.06
     Tells
    0.06
     ".
    0.06
    zí
    0.06
     stark
    0.06
     eleg
    0.06
     panic
    0.06
    Activations Density 0.024%

    No Known Activations