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. 84666
    Prev
    Next
    INDEX
    Explanations

    /latest

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of “latest” (and the adjacent “User”) in AWS documentation URLs, i.e. it detects links to the “latest/UserGuide” sections of the AWS CloudFormation docs.

    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
    (writer
    -0.07
     birbir
    -0.07
     bfs
    -0.06
    adb
    -0.06
    greso
    -0.06
    gresql
    -0.06
    mb
    -0.06
    adores
    -0.06
    ıcı
    -0.06
    توبر
    -0.06
    POSITIVE LOGITS
    /latest
    0.12
    .toDouble
    0.07
    ね
    0.07
     derivation
    0.07
     credentials
    0.07
     ikt
    0.07
     BASE
    0.06
     listening
    0.06
    _back
    0.06
     bidding
    0.06
    Activations Density 0.000%

    No Known Activations