© 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. 57837
    Prev
    Next
    INDEX
    Explanations

    articles and prepositions

    np_max-act · gemini-2.0-flash

    The neuron fires on ChatML header‐boundary tokens (e.g. the “<|start_header_id|>” markers), i.e. it detects the document’s header section delimiters.

    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
     soğuk
    -0.07
    igin
    -0.06
    _expiry
    -0.06
    DEM
    -0.06
    ैय
    -0.06
    .setLayout
    -0.06
     rebound
    -0.06
     ymin
    -0.06
     proxies
    -0.06
    dım
    -0.06
    POSITIVE LOGITS
    <body
    0.08
    νώ
    0.07
    .BigDecimal
    0.07
     خوان
    0.06
    _GAIN
    0.06
     <$
    0.06
    优势
    0.06
    .rcParams
    0.06
    ("\
    0.06
    RenderingContext
    0.06
    Activations Density 0.043%

    No Known Activations