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. 86252
    Prev
    Next
    INDEX
    Explanations

    software development

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric tokens (e.g. version numbers, years, or other standalone numbers).

    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
    ніп
    -0.07
    vc
    -0.06
    secs
    -0.06
     SNAP
    -0.06
     πε
    -0.06
    .hw
    -0.06
    hod
    -0.06
     lao
    -0.06
    ль
    -0.06
    aft
    -0.06
    POSITIVE LOGITS
    .GetKeyDown
    0.07
    _oct
    0.07
    veç
    0.06
     Rach
    0.06
    escaping
    0.06
    (sigma
    0.06
     holy
    0.06
     hiç
    0.06
     داشتن
    0.06
    lbrakk
    0.06
    Activations Density 0.117%

    No Known Activations