© 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. 73838
    Prev
    Next
    INDEX
    Explanations

    negation

    np_max-act · gemini-2.0-flash

    The neuron is triggered by negation words—especially “not” or its contractions—marking inability or failure (e.g. “could not,” “couldn’t,” “didn’t”).

    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
     salvation
    -0.07
    _Static
    -0.07
    亭
    -0.06
    -z
    -0.06
     cruz
    -0.06
    _UT
    -0.06
    альному
    -0.06
    _chain
    -0.06
    _IR
    -0.06
    _IA
    -0.06
    POSITIVE LOGITS
     thuế
    0.06
    RANDOM
    0.06
    iyle
    0.06
    CodeGen
    0.06
    ์การ
    0.06
    SCRIPT
    0.06
     흔
    0.06
     repreh
    0.06
     düzenlenen
    0.06
    	child
    0.06
    Activations Density 0.015%

    No Known Activations