© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 110073
    Prev
    Next
    INDEX
    Explanations

    criticism and controversy

    np_max-act · gemini-2.0-flash

    This neuron activates on nontrivial Spanish content words (longer nouns/adjectives) rather than on common function words or markup.

    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
    427
    -0.06
    Home
    -0.06
    ines
    -0.06
     Duty
    -0.06
     glasses
    -0.06
    가요
    -0.05
    ırı
    -0.05
     Stuart
    -0.05
     Guidelines
    -0.05
     XF
    -0.05
    POSITIVE LOGITS
     شيء
    0.07
     افز
    0.07
    ,ev
    0.07
     COLL
    0.06
    -important
    0.06
     быстро
    0.06
    drive
    0.06
     succès
    0.06
    thinkable
    0.06
     ########.
    0.06
    Activations Density 0.063%

    No Known Activations