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. 40421
    Prev
    Next
    INDEX
    Explanations

    animated

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of animation (e.g. the word “animated” or “Animation”).

    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
     usb
    -0.06
    isch
    -0.06
     Maze
    -0.06
     đu
    -0.06
    _RS
    -0.06
    豆
    -0.06
     iod
    -0.06
     sport
    -0.06
     STREET
    -0.06
     Beetle
    -0.06
    POSITIVE LOGITS
     -------------
    0.07
    (Character
    0.07
    .turn
    0.07
     />\
    0.07
    png
    0.07
    -unit
    0.06
    .amazonaws
    0.06
    every
    0.06
     浙江
    0.06
     incredible
    0.06
    Activations Density 0.004%

    No Known Activations