© 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. 9184
    Prev
    Next
    INDEX
    Explanations

    attention

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the term “attention” (especially when paired with “mechanism”), i.e. it detects mentions of attention mechanisms.

    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
    ฤด
    -0.07
     сервер
    -0.07
    محمد
    -0.07
    _crit
    -0.06
    ()]↵↵
    -0.06
    -report
    -0.06
    --[[
    -0.06
    .exports
    -0.06
    =wx
    -0.06
     behaved
    -0.06
    POSITIVE LOGITS
     Techn
    0.07
    itates
    0.07
    eneral
    0.07
     capture
    0.07
     Ai
    0.06
    	opt
    0.06
     shitty
    0.06
     M
    0.06
    Venue
    0.06
    "...
    0.06
    Activations Density 0.003%

    No Known Activations