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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 37907
    Prev
    Next
    INDEX
    Explanations

    Bariatric surgery

    np_max-act · gemini-2.0-flash

    The neuron activates on the character sequence “ric,” especially as part of words like “bariatric” or “gastric.”

    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
    ΜΑΤ
    -0.06
    pmat
    -0.06
     Karlov
    -0.06
    minated
    -0.06
     hone
    -0.06
    .mkdir
    -0.06
    ันย
    -0.06
    )">
    -0.06
    _LAYOUT
    -0.06
     bowed
    -0.05
    POSITIVE LOGITS
    fastcall
    0.08
    Brandon
    0.07
     Participant
    0.06
     espera
    0.06
    ณะ
    0.06
    @mail
    0.06
    OfWork
    0.06
    lesc
    0.06
     klar
    0.06
     mistake
    0.06
    Activations Density 0.002%

    No Known Activations