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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 85825
    Prev
    Next
    INDEX
    Explanations

    start, begin

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens used to mark structured comment section boundaries—e.g. “start” in HTML comments and “begin-user-doc”/“end-user-doc” in JavaDoc.

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

    HTML elements and metadata related to software documentation.

    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
    unprocessable
    -0.08
     nhé
    -0.07
    ň
    -0.06
    .isLoggedIn
    -0.06
    .reg
    -0.06
    Palette
    -0.06
    	prev
    -0.06
    Pref
    -0.06
     pip
    -0.06
    progressbar
    -0.06
    POSITIVE LOGITS
     Judicial
    0.08
     disciplinary
    0.07
    ).'</
    0.07
     directives
    0.06
    uzzle
    0.06
     піс
    0.06
    ='<
    0.06
    جميع
    0.06
    แม
    0.06
    vh
    0.06
    Activations Density 0.002%

    No Known Activations