© 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. 68442
    Prev
    Next
    INDEX
    Explanations

    improvement

    np_max-act · gemini-2.0-flash

    This neuron fires on Spanish words and phrases related to (incremental) improvement—especially the root “mejor-” as in mejorar, mejora, mejoría, etc.

    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
    (mappedBy
    -0.08
    ,F
    -0.07
    (CancellationToken
    -0.07
     Suspension
    -0.07
    DataProvider
    -0.07
    _SEQUENCE
    -0.07
    cooldown
    -0.06
     Scope
    -0.06
    (scan
    -0.06
    [ch
    -0.06
    POSITIVE LOGITS
    enzyme
    0.07
     Extremely
    0.06
     addicted
    0.06
    -pro
    0.06
    　ﾉ
    0.06
    otti
    0.06
    ductory
    0.06
    點
    0.06
     taş
    0.06
     pointless
    0.06
    Activations Density 0.047%

    No Known Activations