© 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. 5953
    Prev
    Next
    INDEX
    Explanations

    HTML comments

    np_max-act · gemini-2.0-flash

    metadata and structural elements related to HTML documents.

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

    This neuron is primarily activated by HTML comment delimiters (e.g. the “<!--” that opens a comment block).

    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
    -thumb
    -0.07
    แปลง
    -0.06
    gettext
    -0.06
    Cfg
    -0.06
     学
    -0.06
    调整
    -0.06
     prt
    -0.06
    Fmt
    -0.06
    _PROP
    -0.06
    functional
    -0.06
    POSITIVE LOGITS
    wią
    0.07
    iland
    0.07
    など
    0.06
    SCRI
    0.06
     kiş
    0.06
    abyte
    0.06
     performances
    0.06
    !
    0.06
     â
    0.06
     Sophie
    0.06
    Activations Density 0.001%

    No Known Activations