© 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. 74777
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    The neuron activates on browser names and their version numbers (e.g. “IE 8”, “Chrome 13+”, “Firefox 14+”, “Safari 5+”, etc.).

    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
    627
    -0.07
    FlowLayout
    -0.07
    .endTime
    -0.07
    .backgroundColor
    -0.06
     Вик
    -0.06
    circ
    -0.06
     fillColor
    -0.06
     ฝ
    -0.06
     учит
    -0.06
    яч
    -0.06
    POSITIVE LOGITS
    Shop
    0.07
    ighet
    0.07
    ीआई
    0.07
    raising
    0.06
     adore
    0.06
     postage
    0.06
    _TEMPLATE
    0.06
    .Diagnostics
    0.06
     웃
    0.06
     Как
    0.06
    Activations Density 0.007%

    No Known Activations