© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 38085
    Prev
    Next
    INDEX
    Explanations

    Examples and illustrations

    np_max-act · gemini-2.0-flash

    The neuron detects discourse markers—verbs and adverbs like “illustrate,” “emphasise,” “let’s,” and “precisely”—used to introduce or emphasize explanatory points.

    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
     awake
    -0.07
    OnError
    -0.07
    してる
    -0.06
    .randrange
    -0.06
    Explorer
    -0.06
    airport
    -0.06
     Sheldon
    -0.06
    _generation
    -0.06
    ้ผ
    -0.06
    verity
    -0.06
    POSITIVE LOGITS
    ánh
    0.07
    ofi
    0.06
    isches
    0.06
    subpackage
    0.06
    ТО
    0.06
     spokeswoman
    0.06
    createQuery
    0.06
    Bell
    0.06
    >,↵
    0.06
     pří
    0.06
    Activations Density 0.036%

    No Known Activations