© 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. 57000
    Prev
    Next
    INDEX
    Explanations

    objective reporting

    np_max-act · gemini-2.0-flash

    This neuron is sensitive to Latin‐derived word endings—particularly the adjective/verb suffixes like “-al” or “-aria” found in Portuguese (and similar Romance‐language) forms.

    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
    	fp
    -0.08
     kitchens
    -0.07
    master
    -0.06
     Bernard
    -0.06
    agh
    -0.06
    -simple
    -0.06
     parler
    -0.06
     approve
    -0.06
     ї
    -0.06
     gratuito
    -0.06
    POSITIVE LOGITS
    utral
    0.06
    REFERENCES
    0.06
     tweet
    0.06
    ismet
    0.06
    vestment
    0.06
    =&
    0.06
    ΗΣ
    0.06
    .','
    0.05
     reversible
    0.05
     contested
    0.05
    Activations Density 0.367%

    No Known Activations