© 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. 56999
    Prev
    Next
    INDEX
    Explanations

    French

    np_max-act · gemini-2.0-flash

    references to video formats and specific video recording devices.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron activates on French negation constructions, particularly the “ne … pas” pattern in sentences.

    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
     bz
    -0.06
     Schw
    -0.06
     SMART
    -0.06
     المس
    -0.06
     لق
    -0.06
     MOR
    -0.06
     SAS
    -0.06
     SN
    -0.06
     FCC
    -0.06
    bike
    -0.06
    POSITIVE LOGITS
    واره
    0.07
    mouseleave
    0.07
     uvol
    0.07
    ائي
    0.07
     شكل
    0.07
    .Field
    0.07
     Return
    0.07
     redesign
    0.07
     документ
    0.07
    _Public
    0.07
    Activations Density 0.019%

    No Known Activations