© 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. 109187
    Prev
    Next
    INDEX
    Explanations

    .example

    np_max-act · gemini-2.0-flash

    code snippets related to Android application structure and functionality.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects dot-prefixed identifiers in Java code, i.e. segments of package or class names like “.example” or “.test.”

    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
    owany
    -0.07
     Maurit
    -0.07
     //
    ↵
    ↵
    -0.06
     सबस
    -0.06
    ]↵↵↵
    -0.06
    ή
    -0.06
    boats
    -0.06
     проход
    -0.06
    bed
    -0.06
    xD
    -0.06
    POSITIVE LOGITS
    .example
    0.09
     الجن
    0.08
    	help
    0.07
    _esc
    0.07
     assertions
    0.07
     consume
    0.06
    \
    0.06
     earned
    0.06
    .logs
    0.06
    .endTime
    0.06
    Activations Density 0.001%

    No Known Activations