© 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. 130160
    Prev
    Next
    INDEX
    Explanations

    Punctuation

    np_max-act · gemini-2.0-flash

    movie titles with strong thematic elements.

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

    The neuron detects enumeration markers in a numbered list, i.e. the tokens representing list item numbers (digits and their accompanying punctuation).

    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
    ž
    -0.07
    _growth
    -0.07
     tento
    -0.07
    pedido
    -0.07
    وج
    -0.06
    č
    -0.06
     딸
    -0.06
     pits
    -0.06
    (commands
    -0.06
     pushViewController
    -0.06
    POSITIVE LOGITS
     sidewalk
    0.07
    ="--
    0.06
     sidewalks
    0.06
     shifted
    0.06
     mobil
    0.06
    DN
    0.06
     matures
    0.06
     warranty
    0.06
     magically
    0.06
     buyer
    0.06
    Activations Density 0.018%

    No Known Activations