© 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. 56761
    Prev
    Next
    INDEX
    Explanations

    Zoological publications

    np_max-act · gemini-2.0-flash

    specific scientific names and classifications of organisms.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on bibliographic reference and taxonomy citation strings—i.e. lines carrying scientific publication details (authors, journal or book titles, years, volume/page numbers, and taxonomic ranks).

    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
    STRUCTOR
    -0.07
     cognition
    -0.07
     Anne
    -0.06
    _THROW
    -0.06
     deadlines
    -0.06
     evento
    -0.06
    Fashion
    -0.06
    (di
    -0.06
    An
    -0.06
    .Selection
    -0.06
    POSITIVE LOGITS
    ">×</
    0.06
     DRV
    0.06
     synonymous
    0.06
     Portable
    0.06
    озем
    0.06
     blinking
    0.06
     monthly
    0.06
     Seed
    0.06
    [MAX
    0.06
    вещ
    0.06
    Activations Density 0.007%

    No Known Activations