© 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. 91188
    Prev
    Next
    INDEX
    Explanations

    interest

    np_max-act · gemini-2.0-flash

    This neuron detects structural markup tokens and metadata (e.g. conversation role tags and special delimiters) rather than actual content.

    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
    pees
    -0.06
     Parses
    -0.06
    mdat
    -0.06
    ९
    -0.06
    鲁
    -0.06
     Scheduler
    -0.05
    literal
    -0.05
     weeks
    -0.05
    	code
    -0.05
    _BIT
    -0.05
    POSITIVE LOGITS
    /ubuntu
    0.07
     algorithm
    0.07
     occured
    0.07
    Scheme
    0.07
     AFF
    0.07
     کارخانه
    0.07
     concl
    0.07
     uplift
    0.06
    artisan
    0.06
    /admin
    0.06
    Activations Density 0.006%

    No Known Activations