© 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. 54151
    Prev
    Next
    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on inline CSS style declarations—especially numeric property values (e.g. “height: 56px”) in HTML style attributes.

    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
    Sampler
    -0.07
     их
    -0.07
    early
    -0.07
    washing
    -0.07
    .groups
    -0.06
    (unittest
    -0.06
    yclopedia
    -0.06
    _gshared
    -0.06
    eket
    -0.06
     Keeper
    -0.06
    POSITIVE LOGITS
     todo
    0.07
    dens
    0.06
     erotik
    0.06
    ilio
    0.06
    jeta
    0.06
     возв
    0.06
     seis
    0.06
     �
    0.06
     他
    0.06
     MSM
    0.06
    Activations Density 0.004%

    No Known Activations