© 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. 127012
    Prev
    Next
    INDEX
    Explanations

    quantities

    np_max-act · gemini-2.0-flash

    This neuron activates on the word “multiple” (i.e. occurrences of “multiple” indicating more than one).

    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
     eater
    -0.07
    -Mart
    -0.07
    říž
    -0.07
    -business
    -0.07
     intimidation
    -0.06
     Shel
    -0.06
     decoder
    -0.06
    ंश
    -0.06
     Succ
    -0.06
     tire
    -0.06
    POSITIVE LOGITS
    ']);
    0.07
     metaph
    0.06
     тех
    0.06
    しない
    0.06
    $con
    0.06
    ?</
    0.06
    void
    0.06
     ajout
    0.06
    нив
    0.06
     코
    0.06
    Activations Density 0.066%

    No Known Activations