© 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. 124916
    Prev
    Next
    INDEX
    Explanations

    question answering

    np_max-act · gemini-2.0-flash

    The neuron detects the standard opening phrases or acknowledgments (e.g. “Sure, here’s the requested information…”) at the start of an assistant reply.

    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
    ipt
    -0.06
     PAD
    -0.06
    .DataGridViewColumnHeadersHeightSizeMode
    -0.06
    /cli
    -0.06
     покуп
    -0.06
    .Ext
    -0.06
     注意
    -0.06
    елення
    -0.06
    controller
    -0.06
     logits
    -0.06
    POSITIVE LOGITS
    (gulp
    0.07
    يون
    0.07
     building
    0.07
     tomb
    0.06
     buildings
    0.06
    ฤด
    0.06
     voyeur
    0.06
     legit
    0.06
     draw
    0.06
    πέ
    0.06
    Activations Density 0.008%

    No Known Activations