© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 58234
    Prev
    Next
    INDEX
    Explanations

    antim

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of “antimatter” (and its subword components like “antim” + “atter”) or related antimatter particle terms.

    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
     Hiring
    -0.07
     �
    -0.06
    .cd
    -0.06
     ------------------------------------------------------------------------↵
    -0.06
    顶
    -0.06
     dunk
    -0.06
     traverse
    -0.06
    (errors
    -0.06
    (users
    -0.06
    ทร
    -0.06
    POSITIVE LOGITS
     etm
    0.08
    _NT
    0.07
     mitochondrial
    0.07
     microwave
    0.07
    +/
    0.07
    togroup
    0.07
     synd
    0.07
    ::$
    0.07
    imest
    0.07
     deque
    0.07
    Activations Density 0.003%

    No Known Activations