© 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. 6103
    Prev
    Next
    INDEX
    Explanations

    colors

    np_max-act · gemini-2.0-flash

    The neuron fires on color and style tokens (e.g. color names like “green,” “red,” “blue,” and style keywords such as “dashed”).

    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
    物
    -0.06
     củ
    -0.06
    Advertisement
    -0.06
    Two
    -0.06
    "My
    -0.06
    (skip
    -0.06
     kd
    -0.06
    .Resource
    -0.06
     پرداز
    -0.06
    CallableWrapper
    -0.06
    POSITIVE LOGITS
     فبراير
    0.06
    usher
    0.06
     userEmail
    0.06
    XHR
    0.06
     clam
    0.06
    _damage
    0.06
    ----------------
    0.06
    .payment
    0.06
     Alabama
    0.06
     Norfolk
    0.06
    Activations Density 0.013%

    No Known Activations