© 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. 9424
    Prev
    Next
    INDEX
    Explanations

    Punctuation

    np_max-act · gemini-2.0-flash

    The neuron reliably spikes whenever the text switches into code‐like or markup sections (e.g. programming syntax, tags, fenced code blocks) rather than ordinary prose.

    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
    _Image
    -0.06
    735
    -0.06
     peek
    -0.06
     babys
    -0.06
    626
    -0.06
    260
    -0.06
    ,input
    -0.06
     chk
    -0.06
     hoạt
    -0.06
    369
    -0.06
    POSITIVE LOGITS
    桑
    0.07
    (enable
    0.07
    ">',↵
    0.07
     Dane
    0.07
    assuming
    0.06
    적
    0.06
    �
    0.06
    Former
    0.06
    .execSQL
    0.06
     بأ
    0.06
    Activations Density 0.074%

    No Known Activations