© 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. 56668
    Prev
    Next
    INDEX
    Explanations

    ological

    np_max-act · gemini-2.0-flash

    The neuron activates strongly on occurrences of the word “topological” (especially the “ological” token) whenever topological phases or phenomena are discussed.

    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
     load
    -0.08
    (raw
    -0.07
    _PAIR
    -0.07
     pdata
    -0.07
     XY
    -0.07
    odzi
    -0.07
     Gary
    -0.06
    cba
    -0.06
     люд
    -0.06
     complexes
    -0.06
    POSITIVE LOGITS
    ElapsedTime
    0.07
     refund
    0.06
    농
    0.06
    elling
    0.06
     clicked
    0.06
    tabl
    0.06
    -अ
    0.06
    "",↵
    0.06
     regularly
    0.06
    Disclosure
    0.06
    Activations Density 0.002%

    No Known Activations