© 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. 7722
    Prev
    Next
    INDEX
    Explanations

    synth

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of the name “pyinstaller,” i.e. it detects mentions of the PyInstaller module.

    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
    voir
    -0.08
     inquiry
    -0.07
    rů
    -0.07
    ()},
    -0.07
     Katz
    -0.06
     addiction
    -0.06
     Sonic
    -0.06
    	tp
    -0.06
     Qatar
    -0.06
    elters
    -0.06
    POSITIVE LOGITS
     избав
    0.06
    .IMAGE
    0.06
     underestimate
    0.06
     scrub
    0.06
    ВО
    0.06
    ща
    0.06
    за
    0.06
    'app
    0.06
    mq
    0.06
    _countries
    0.06
    Activations Density 0.456%

    No Known Activations