© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 128664
    Prev
    Next
    INDEX
    Explanations

    Describing locations or components

    np_max-act · gemini-2.0-flash

    references to genetic markers associated with breast cancer and their implications.

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

    The neuron specializes in spotting numeric measurement expressions—decimal numbers (and their accompanying units) in the text.

    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
    inou
    -0.07
     τα
    -0.07
    dropout
    -0.07
    _ignore
    -0.06
    ilig
    -0.06
     Type
    -0.06
     başına
    -0.06
     ist
    -0.06
     push
    -0.06
     turnaround
    -0.06
    POSITIVE LOGITS
     Martian
    0.07
     (=
    0.06
     мод
    0.06
     empirical
    0.06
     acl
    0.06
     boots
    0.06
    ANTLR
    0.06
     frontal
    0.06
     первого
    0.06
     mRNA
    0.06
    Activations Density 0.109%

    No Known Activations