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

    Neuronpedia

    Jacobian LensNEW
    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. 56934
    Prev
    Next
    INDEX
    Explanations

    "

    np_max-act · gemini-2.0-flash

    The neuron flags Chinese-script characters or transliterated Chinese syllables 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
    KW
    -0.07
     cellpadding
    -0.07
     lent
    -0.07
    MW
    -0.06
     Reviews
    -0.06
     Technician
    -0.06
     cerebral
    -0.06
     만
    -0.06
     Brew
    -0.06
    _frequency
    -0.06
    POSITIVE LOGITS
     Jerry
    0.06
    oyal
    0.06
     escalated
    0.06
    kept
    0.06
    ounce
    0.06
    TOOLS
    0.06
    λιο
    0.05
    iddle
    0.05
     bb
    0.05
    овали
    0.05
    Activations Density 0.078%

    No Known Activations