© 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. 43102
    Prev
    Next
    INDEX
    Explanations

    positive sentiment

    np_max-act · gemini-2.0-flash

    The neuron activates on words expressing gratitude or enthusiastic positive sentiment (e.g. “reconnaissant,” “enthousiaste”) in polite correspondence.

    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
     エ
    -0.06
     tedavi
    -0.06
    .species
    -0.06
     ingredient
    -0.06
     pleading
    -0.06
     cann
    -0.06
    ();

↵
    -0.06
    eligible
    -0.06
    Thousands
    -0.06
    477
    -0.06
    POSITIVE LOGITS
     Ordering
    0.07
     přisp
    0.06
    Too
    0.06
     نوفمبر
    0.06
    .internal
    0.06
     حق
    0.06
    nah
    0.06
     vein
    0.06
     Points
    0.06
    readcrumbs
    0.06
    Activations Density 0.039%

    No Known Activations