© 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. 38458
    Prev
    Next
    INDEX
    Explanations

    research

    np_max-act · gemini-2.0-flash

    The neuron is sensitive to verbs that describe research actions or experimental methods (e.g. “investigated,” “performed,” “evaluated,” “described”) in scientific texts.

    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
     followers
    -0.06
    WAIT
    -0.06
    better
    -0.06
     Wash
    -0.06
     Bags
    -0.06
     boiler
    -0.06
    :a
    -0.06
    -0.06
     Invalidate
    -0.06
     призначення
    -0.06
    POSITIVE LOGITS
     koşul
    0.07
     roadway
    0.07
     čís
    0.07
    _crossentropy
    0.07
    adier
    0.07
     Portsmouth
    0.06
     ''),↵
    0.06
    mé
    0.06
     корпус
    0.06
     endereco
    0.06
    Activations Density 0.074%

    No Known Activations