© 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. 7463
    Prev
    Next
    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash

    This neuron responds to occurrences of the word “not.”

    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
    Venta
    -0.07
    Mini
    -0.06
    /core
    -0.06
     Mour
    -0.06
    瑞
    -0.06
    Sy
    -0.06
     jeder
    -0.06
     verdi
    -0.06
     envy
    -0.06
     servicio
    -0.06
    POSITIVE LOGITS
     not
    0.26
     Not
    0.19
    not
    0.19
    't
    0.18
     NOT
    0.18
    ’t
    0.17
    Not
    0.17
     cannot
    0.17
    cannot
    0.16
     doesnt
    0.16
    Activations Density 0.411%

    No Known Activations