© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 110215
    Prev
    Next
    INDEX
    Explanations

    plots

    np_max-act · gemini-2.0-flash

    This neuron activates on LaTeX pgfplots/TikZ command and environment tokens (e.g. “axis,” “tikzpicture,” “pgfplots,” “plot”).

    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
    _BL
    -0.07
    =W
    -0.06
     degraded
    -0.06
    ever
    -0.06
    WARDS
    -0.06
     Роз
    -0.06
    	Optional
    -0.06
     Τε
    -0.06
     Fakült
    -0.06
     recognizer
    -0.06
    POSITIVE LOGITS
     retrofit
    0.07
    fusion
    0.07
    plots
    0.07
    .addRow
    0.07
     politics
    0.06
    <float
    0.06
     thous
    0.06
    -touch
    0.06
     warfare
    0.06
     authorized
    0.06
    Activations Density 0.000%

    No Known Activations