© 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. 7468
    Prev
    Next
    INDEX
    Explanations

    year

    np_max-act · gemini-2.0-flash

    The neuron is sensitive to numeric and quantitative expressions (numbers, percentages, measurements, statistics) in the text.

    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
     elm
    -0.07
    ridge
    -0.07
     sorry
    -0.06
    ูม
    -0.06
    [iVar
    -0.06
    πως
    -0.06
     Nigeria
    -0.06
    /".$
    -0.06
     کال
    -0.06
     Grimm
    -0.06
    POSITIVE LOGITS
    -render
    0.06
    Zen
    0.06
    erea
    0.06
    structor
    0.06
    .notNull
    0.06
    asje
    0.06
    .animation
    0.06
    ethe
    0.06
    Adapter
    0.05
    .Render
    0.05
    Activations Density 0.787%

    No Known Activations