© 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. 6544
    Prev
    Next
    INDEX
    Explanations

    говор

    np_max-act · gemini-2.0-flash

    The neuron activates on Korean words that describe photographic image qualities—specifically terms for “darkness” (어두워질) and “sharpness/clarity” (선명).

    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
     same
    -0.07
    itch
    -0.06
     voc
    -0.06
     closure
    -0.06
     wholly
    -0.06
     значения
    -0.06
     نمونه
    -0.06
    ۸
    -0.06
    aldo
    -0.06
    [x
    -0.06
    POSITIVE LOGITS
    cribing
    0.06
    genres
    0.06
     celkem
    0.06
    entionPolicy
    0.06
     народу
    0.06
     haben
    0.06
     požadav
    0.06
    (trim
    0.06
     Schwarz
    0.06
     freq
    0.06
    Activations Density 0.168%

    No Known Activations