© 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. 73951
    Prev
    Next
    INDEX
    Explanations

    equals

    np_max-act · gemini-2.0-flash

    The neuron consistently activates on the “=” sign in arithmetic expressions, flagging the equality operator in user‐supplied math queries.

    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
    ATFORM
    -0.07
    jsonwebtoken
    -0.07
     Whip
    -0.07
     ups
    -0.07
    џџџџџџџџ
    -0.07
    --){↵
    -0.06
    semi
    -0.06
    .Engine
    -0.06
    hPa
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    child
    0.06
     importing
    0.06
    uj
    0.05
     existence
    0.05
     meth
    0.05
     ğ
    0.05
     tiểu
    0.05
     Georg
    0.05
     menj
    0.05
     Aub
    0.05
    Activations Density 0.023%

    No Known Activations