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

    Neuronpedia

    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. 129867
    Prev
    Next
    INDEX
    Explanations

    final last

    np_max-act · gemini-2.0-flash

    The neuron predominantly lights up on ordinal/final markers—especially the word “last” (and related tokens like “one last”) indicating a final action or event.

    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
     Bennett
    -0.07
     edecek
    -0.07
     fortunately
    -0.06
    .elem
    -0.06
     progressing
    -0.06
    -paid
    -0.06
     Venture
    -0.06
     progressed
    -0.06
     �
    -0.06
     Si
    -0.06
    POSITIVE LOGITS
    Patch
    0.07
     Compatible
    0.07
     cond
    0.06
     pela
    0.06
     mism
    0.06
     mẽ
    0.06
     sofa
    0.06
     nhiệm
    0.06
    Stencil
    0.06
    ）
    0.06
    Activations Density 0.015%

    No Known Activations