© 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. 105560
    Prev
    Next
    INDEX
    Explanations

    off

    np_max-act · gemini-2.0-flash

    The neuron fires on first-person “meta” announcements of the author’s next move—phrases like “I’m off to…,” “I’ll just be…,” or “I’m over here…,” signalling a self-referential departure or upcoming action.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    discussions about social media influencers and their online personas.

    oai_token-act-pair · gpt-4o-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
    _AGENT
    -0.07
    _basic
    -0.07
    [length
    -0.07
    .latest
    -0.07
    .items
    -0.06
    Empty
    -0.06
    (conv
    -0.06
     selves
    -0.06
    	length
    -0.06
     polynomial
    -0.06
    POSITIVE LOGITS
     дуже
    0.07
    ература
    0.07
     các
    0.06
     zase
    0.06
     cara
    0.06
     заяви
    0.06
     стали
    0.06
     sera
    0.06
    /package
    0.06
    .configureTestingModule
    0.06
    Activations Density 0.051%

    No Known Activations