© 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. 830
    Prev
    Next
    INDEX
    Explanations

    color

    np_max-act · gemini-2.0-flash

    This neuron fires on color/fill aesthetic mappings and related scale specifications in ggplot2 code.

    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
     печ
    -0.07
     Εκ
    -0.06
    牛
    -0.06
    )))))↵
    -0.06
     пацієн
    -0.06
    ед
    -0.06
    Histor
    -0.06
     aber
    -0.05
     Beled
    -0.05
     findOne
    -0.05
    POSITIVE LOGITS
    .Quad
    0.08
    .simple
    0.07
    -appointed
    0.07
    _alive
    0.06
    -use
    0.06
    ertainment
    0.06
    _Response
    0.06
    FormattedMessage
    0.06
    Slice
    0.06
    imal
    0.06
    Activations Density 0.003%

    No Known Activations