© 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. 9413
    Prev
    Next
    INDEX
    Explanations

    UI drawing code

    np_max-act · gemini-2.0-flash

    This neuron activates on low-level graphics API calls and related rendering function names (e.g. OpenGL/GLUT display or paint methods).

    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
    ulkan
    -0.07
    ADIO
    -0.07
     spherical
    -0.07
     Stella
    -0.07
    력
    -0.07
    Radio
    -0.07
     Kad
    -0.07
     cooling
    -0.07
     contraction
    -0.07
    лав
    -0.07
    POSITIVE LOGITS
    @register
    0.07
    .IP
    0.06
    /my
    0.06
    _pemb
    0.06
    .BigInteger
    0.06
    „M
    0.06
    .Res
    0.06
    Consult
    0.05
    Так
    0.05
    -Americans
    0.05
    Activations Density 0.033%

    No Known Activations