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. 130364
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron flags numeric tokens (e.g. years, dates, or decimal‐formatted numbers) in the text.

    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
     Antonio
    -0.07
    -ac
    -0.07
    三级
    -0.07
     corros
    -0.06
     dissatisfaction
    -0.06
    EPS
    -0.06
    ea
    -0.06
     ricerca
    -0.06
    Nếu
    -0.06
     Coroutine
    -0.06
    POSITIVE LOGITS
     size
    0.07
    ヴ
    0.07
     gid
    0.07
    (predictions
    0.06
    size
    0.06
    raising
    0.06
    ・マ
    0.06
     đích
    0.06
    성이
    0.06
    аблиц
    0.06
    Activations Density 0.015%

    No Known Activations