© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 13955
    Prev
    Next
    INDEX
    Explanations

    Vintage

    np_max-act · gemini-2.0-flash

    This neuron responds to occurrences of the adjective “vintage” (or “vintage”-type descriptors) 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
     employees
    -0.07
    Leaders
    -0.07
     lecturer
    -0.07
     Universidad
    -0.07
    Head
    -0.07
    <L
    -0.07
     controlled
    -0.06
    @foreach
    -0.06
     let
    -0.06
    Moon
    -0.06
    POSITIVE LOGITS
     vintage
    0.13
     Vintage
    0.11
    Vintage
    0.11
    intage
    0.09
    ique
    0.08
     vieille
    0.07
    :nth
    0.07
    ình
    0.07
     antique
    0.07
    품
    0.07
    Activations Density 0.003%

    No Known Activations