© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 73576
    Prev
    Next
    INDEX
    Explanations

    Yu-Gi-Oh

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of the "Yu-Gi-Oh!" franchise name (and its variants/subtitles like ARC-V) in the text.

    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
     CF
    -0.07
     absurd
    -0.07
     MessageBoxButtons
    -0.06
    _OPER
    -0.06
     अन
    -0.06
    .downcase
    -0.06
     Wander
    -0.06
     Mana
    -0.06
     Ki
    -0.06
     censor
    -0.06
    POSITIVE LOGITS
     науч
    0.07
    thern
    0.07
    аран
    0.06
    loid
    0.06
     mastur
    0.06
     tuberculosis
    0.06
    papers
    0.06
    하우
    0.06
    ्ड
    0.06
    onga
    0.06
    Activations Density 0.007%

    No Known Activations