Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 41964
    Prev
    Next
    INDEX
    Explanations

    dates and prices

    np_max-act · gemini-2.0-flash

    This neuron fires on date‐related header tokens (e.g. the “Date” label in the document header).

    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
    egers
    -0.07
    alpha
    -0.07
     feared
    -0.06
    atching
    -0.06
     Kis
    -0.06
    .Push
    -0.06
    lopedia
    -0.06
     首页第
    -0.06
    gamber
    -0.06
     downloads
    -0.06
    POSITIVE LOGITS
    .gov
    0.06
     проблемы
    0.06
    .people
    0.06
    _Base
    0.06
    Reserved
    0.06
     يو
    0.06
    _picture
    0.06
     Dere
    0.06
    @show
    0.06
    ItemImage
    0.06
    Activations Density 0.015%

    No Known Activations