© 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 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. 38408
    Prev
    Next
    INDEX
    Explanations

    bound

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of an “upper bound,” i.e. phrases referring to upper‐bound estimates in mathematical statements.

    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
    िलत
    -0.06
    fv
    -0.06
    [assembly
    -0.06
    _letters
    -0.06
     Elig
    -0.06
    -feedback
    -0.06
    рест
    -0.06
    一緒
    -0.06
     зміни
    -0.06
    _experience
    -0.06
    POSITIVE LOGITS
    (tb
    0.08
    游
    0.07
    combined
    0.07
    женер
    0.07
    _BE
    0.07
    >n
    0.07
    _then
    0.07
     cris
    0.07
    (front
    0.07
     ImageButton
    0.06
    Activations Density 0.005%

    No Known Activations