© 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. 108940
    Prev
    Next
    INDEX
    Explanations

    disc

    np_max-act · gemini-2.0-flash

    This neuron fires on disc‐golf–specific terminology (words like “disc,” “golf,” “course,” “hole,” “basket,” etc.).

    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
     can
    -0.07
     ladder
    -0.06
    sip
    -0.06
    olt
    -0.06
    olves
    -0.06
     convinced
    -0.06
    动物
    -0.06
    +f
    -0.05
    oves
    -0.05
    _lo
    -0.05
    POSITIVE LOGITS
    (HaveOccurred
    0.07
    )+'
    0.07
     honesty
    0.07
    '")↵
    0.07
     estava
    0.07
     jon
    0.07
     objc
    0.07
    $class
    0.07
    ????????
    0.06
    '];?>"
    0.06
    Activations Density 0.002%

    No Known Activations