© 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. 57234
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    This neuron activates on license‐header boilerplate text (specifically the numbered license clauses, e.g. “1. The origin of this software must not be misrepresented; …”).

    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
    Mary
    -0.07
     Printing
    -0.07
    Rendering
    -0.07
    투
    -0.06
     veteran
    -0.06
    pletely
    -0.06
     её
    -0.06
     Bust
    -0.06
    #
    -0.06
     mentally
    -0.06
    POSITIVE LOGITS
    pector
    0.07
    年に
    0.06
     угл
    0.06
     AudioSource
    0.06
    .interpolate
    0.06
    ンの
    0.06
     kesin
    0.06
     tinh
    0.06
     contradictory
    0.06
    	show
    0.06
    Activations Density 0.001%

    No Known Activations