© 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. 92275
    Prev
    Next
    INDEX
    Explanations

    engineering

    np_max-act · gemini-2.0-flash

    This neuron lights up on specialized technical jargon—particularly multi-syllable compound nouns and domain-specific terms common in patent descriptions.

    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
     кле
    -0.06
     Automatically
    -0.06
     Turtle
    -0.06
     liter
    -0.06
     như
    -0.06
     minutes
    -0.06
    定
    -0.06
    เพราะ
    -0.06
    pter
    -0.06
     seminars
    -0.06
    POSITIVE LOGITS
     змін
    0.06
    ůst
    0.06
     производства
    0.06
    .bit
    0.06
    icals
    0.06
    signature
    0.06
     HG
    0.06
     acknowledge
    0.06
     Ryzen
    0.06
     fallback
    0.06
    Activations Density 0.228%

    No Known Activations