© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 101582
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on the punctuation and numeric bits of structured code/markup—slashes, colons, decimal numbers, equals signs, IDs and similar tokens in XML‐style tags or file/path identifiers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    details related to XML or structured data formats.

    oai_token-act-pair · gpt-4o-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
    iate
    -0.07
    .speed
    -0.06
    rous
    -0.06
     cock
    -0.06
    國
    -0.06
    あの
    -0.06
    Coll
    -0.06
    Iron
    -0.06
    €€€€
    -0.06
    -du
    -0.06
    POSITIVE LOGITS
     Ranked
    0.07
     Guaranteed
    0.07
    .'</
    0.07
     {(
    0.07
    .sz
    0.06
     clinically
    0.06
    uti
    0.06
     ISR
    0.06
    @api
    0.06
    livé
    0.06
    Activations Density 0.019%

    No Known Activations