© 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. 38560
    Prev
    Next
    INDEX
    Explanations

    beginnings and establishments

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of key founding or initiation events, i.e. verbs and phrases describing when something is created, established, opened, approved, or begins.

    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
     tonnes
    -0.07
    AFP
    -0.06
    (U
    -0.06
     Moj
    -0.06
    Due
    -0.06
     Γου
    -0.06
     EE
    -0.06
    [of
    -0.06
     STAT
    -0.06
     tread
    -0.06
    POSITIVE LOGITS
    +',
    0.07
    ")]↵
    0.06
    ชร
    0.06
     özel
    0.06
     землю
    0.06
     zih
    0.06
     clr
    0.06
     بخش
    0.06
    ')):↵
    0.06
    ',↵
    0.06
    Activations Density 0.085%

    No Known Activations