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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 84411
    Prev
    Next
    INDEX
    Explanations

    number symbols

    np_max-act · gemini-2.0-flash

    This neuron responds to the numeric parts of legal case or docket identifiers (e.g. the “No. 9,” “No. 1,” etc. in case citations).

    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
     hut
    -0.06
    ibia
    -0.06
    astes
    -0.06
    thumbnails
    -0.06
     Rifle
    -0.06
    @login
    -0.06
     property
    -0.06
    ┃
    -0.06
    AQ
    -0.06
     pix
    -0.06
    POSITIVE LOGITS
    ív
    0.07
    -quarters
    0.06
    doubleValue
    0.06
    key
    0.06
    тех
    0.06
    metatable
    0.06
     nouve
    0.06
     zurück
    0.06
     răng
    0.06
    σεων
    0.06
    Activations Density 0.005%

    No Known Activations