© 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 EvalsExportsinterp-engineNEWAPI 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. 57843
    Prev
    Next
    INDEX
    Explanations

    an

    np_max-act · gemini-2.0-flash

    program-related licensing terms and structures.

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

    The neuron specifically fires on the “an” in the recurring Apache‐License boilerplate phrase “distributed on an ‘AS IS’ BASIS.”

    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
     IN
    -0.07
     soo
    -0.07
    	ON
    -0.06
    	con
    -0.06
    KO
    -0.06
     OK
    -0.06
    assignment
    -0.06
     答
    -0.06
    г
    -0.06
     ERP
    -0.06
    POSITIVE LOGITS
    .none
    0.06
     (~(
    0.06
     Decom
    0.06
    COMM
    0.06
    झ
    0.06
     Minh
    0.06
     βα
    0.06
     highlights
    0.06
     حم
    0.05
     объем
    0.05
    Activations Density 0.001%

    No Known Activations