© 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. 54374
    Prev
    Next
    INDEX
    Explanations

    knights and chivalry

    np_max-act · gemini-2.0-flash

    The neuron fires strongly on subword pieces of “chivalry” (ch-, ival-, ‑ry) and related courtly/knightly virtue terms (honor, courtly, knight), so it is detecting references to medieval chivalric concepts.

    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
     missionaries
    -0.07
     downt
    -0.06
    iled
    -0.06
    ui
    -0.06
    коп
    -0.06
    徐
    -0.06
    ordo
    -0.06
     tongues
    -0.06
    explained
    -0.06
     Hazel
    -0.06
    POSITIVE LOGITS
     гаран
    0.06
     등록
    0.06
    が出
    0.06
    ="/">↵
    0.06
    kening
    0.06
    staticmethod
    0.06
    	glBind
    0.06
    Legal
    0.06
    (Expression
    0.06
    Chris
    0.06
    Activations Density 0.040%

    No Known Activations