© 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. 56384
    Prev
    Next
    INDEX
    Explanations

    News articles

    np_max-act · gemini-2.0-flash

    The neuron fires on the common reporting and auxiliary verbs used in news‐style present-tense statements (e.g. “are,” “is,” “said,” “explained,” “working”).

    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
     Treasury
    -0.07
    Bug
    -0.07
     multiplying
    -0.07
     róż
    -0.07
    yh
    -0.06
    Prefs
    -0.06
     cafes
    -0.06
     Maggie
    -0.06
     DAN
    -0.06
     Far
    -0.06
    POSITIVE LOGITS
    obra
    0.07
    @author
    0.06
     quân
    0.06
    -cookie
    0.06
    \Input
    0.06
    interopRequireDefault
    0.06
     groundbreaking
    0.06
     Kawasaki
    0.06
     regexp
    0.06
     Templ
    0.06
    Activations Density 0.154%

    No Known Activations