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. 84501
    Prev
    Next
    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash

    The neuron activates on the key countable‐object nouns in simple arithmetic word problems (e.g. “cars,” “golf balls,” “trees”).

    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
    .top
    -0.07
    .Source
    -0.07
    ),"
    -0.07
    -figure
    -0.06
     Listener
    -0.06
    .ViewModel
    -0.06
     المق
    -0.06
    .Top
    -0.06
    “To
    -0.06
     Tome
    -0.06
    POSITIVE LOGITS
    िज
    0.06
     reserv
    0.06
     intended
    0.06
    �
    0.06
    �
    0.06
    证
    0.06
    狂
    0.06
    挙
    0.06
     SCALE
    0.06
    かな
    0.06
    Activations Density 0.012%

    No Known Activations