© 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. 65197
    Prev
    Next
    INDEX
    Explanations

    opposite

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the word “opposite.”

    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
    .tests
    -0.08
     Sheldon
    -0.08
     Freel
    -0.07
     安
    -0.07
    ソン
    -0.07
     科
    -0.07
     Wells
    -0.07
     JD
    -0.07
     Weld
    -0.07
     caves
    -0.07
    POSITIVE LOGITS
     opposite
    0.16
    _same
    0.08
     oppos
    0.08
     contrary
    0.07
    posite
    0.07
    ีผ
    0.07
     mismo
    0.07
    .same
    0.07
    끼
    0.07
    ‐‐
    0.07
    Activations Density 0.005%

    No Known Activations