© 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. 74782
    Prev
    Next
    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric tokens—especially instances of the digit “4” in contexts like “last 4 digits.”

    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
    nému
    -0.07
    payload
    -0.07
     poc
    -0.06
     infection
    -0.06
     ran
    -0.06
     Ruf
    -0.06
     мон
    -0.06
     нею
    -0.06
     oo
    -0.06
     coppia
    -0.06
    POSITIVE LOGITS
    (['/
    0.06
     eski
    0.06
    楽
    0.06
     pylint
    0.06
    MX
    0.06
     compounded
    0.06
     express
    0.05
    eventName
    0.05
    	JSONObject
    0.05
     قن
    0.05
    Activations Density 0.004%

    No Known Activations