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

    Neuronpedia

    APICircuit 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. 40434
    Prev
    Next
    INDEX
    Explanations

    stuck

    np_max-act · gemini-2.0-flash

    The neuron detects when the text includes the word “stuck,” i.e. the user saying they’re stuck.

    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
    Integration
    -0.07
     tươi
    -0.06
    _deinit
    -0.06
    Merit
    -0.06
     lối
    -0.06
     qualité
    -0.06
    ises
    -0.06
    .progressBar
    -0.06
    Datetime
    -0.06
    .business
    -0.06
    POSITIVE LOGITS
     stuck
    0.12
     trapped
    0.09
     �
    0.07
     Hük
    0.07
     sanki
    0.07
    rtc
    0.06
    ังหว
    0.06
     stalking
    0.06
     حک
    0.06
     půl
    0.06
    Activations Density 0.004%

    No Known Activations