© 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. 571
    Prev
    Next
    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash

    Vue component structures and their interactions with Tailwind CSS.

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

    The neuron detects the curly‐brace delimiters used in JavaScript object literals (e.g. the “{” and “}” around export default objects).

    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
    ीश
    -0.07
     Sevilla
    -0.07
    "How
    -0.06
    JKLMNOP
    -0.06
    _TRAN
    -0.06
     odp
    -0.06
    erable
    -0.06
    (Collections
    -0.06
    _npc
    -0.06
    ductory
    -0.06
    POSITIVE LOGITS
    emploi
    0.07
    Disable
    0.06
    dispatch
    0.06
    ğin
    0.06
     Sel
    0.06
     tüm
    0.06
    ındır
    0.06
     wording
    0.06
     disappearing
    0.06
    according
    0.06
    Activations Density 0.002%

    No Known Activations