© 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. 7250
    Prev
    Next
    INDEX
    Explanations

    generated

    np_max-act · gemini-2.0-flash

    This neuron responds to occurrences of the verb “generated” (and closely related causal/time-marker words like “due” and “during”) indicating something being produced.

    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
     Record
    -0.07
     clean
    -0.06
    융
    -0.06
     OV
    -0.06
    InterruptedException
    -0.06
     какие
    -0.06
     Мак
    -0.06
     останні
    -0.06
    .ReadAll
    -0.06
    localObject
    -0.06
    POSITIVE LOGITS
    CppClass
    0.08
     erf
    0.07
    /md
    0.07
    xd
    0.07
     dispenser
    0.07
    -peer
    0.06
     سخن
    0.06
    òi
    0.06
     UIButton
    0.06
     ltd
    0.06
    Activations Density 0.033%

    No Known Activations