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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 88912
    Prev
    Next
    INDEX
    Explanations

    who

    np_max-act · gemini-2.0-flash

    This neuron activates on the relative pronoun “who” when it introduces a clause (e.g. “who were …”).

    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
    .dist
    -0.06
    (sec
    -0.06
     strtok
    -0.06
     mosquitoes
    -0.06
     Flesh
    -0.06
     Inherits
    -0.06
    _CN
    -0.06
     Translator
    -0.06
    SER
    -0.06
     Respond
    -0.06
    POSITIVE LOGITS
    623
    0.06
     링
    0.06
     gladly
    0.06
     vacuum
    0.06
    ,''
    0.06
    Minnesota
    0.06
     політи
    0.06
    -W
    0.06
     guesses
    0.06
     겨
    0.06
    Activations Density 0.000%

    No Known Activations