© 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. 9256
    Prev
    Next
    INDEX
    Explanations

    code, programming

    np_max-act · gemini-2.0-flash

    The neuron activates on coding‐instruction verbs and similar action words (e.g. “use,” “change,” “add,” “allow,” “cannot”) in programming how-to 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
    .sign
    -0.06
     Vib
    -0.06
    azing
    -0.06
     plates
    -0.06
     ting
    -0.06
     loft
    -0.06
    home
    -0.06
     Nicola
    -0.06
    CA
    -0.06
    kit
    -0.06
    POSITIVE LOGITS
     концеп
    0.07
    랫
    0.07
     Trio
    0.07
    Posted
    0.07
     lekker
    0.06
     مصر
    0.06
     Spotify
    0.06
    ити
    0.06
     svensk
    0.06
     آس
    0.06
    Activations Density 0.132%

    No Known Activations