© 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. 7610
    Prev
    Next
    INDEX
    Explanations

    research

    np_max-act · gemini-2.0-flash

    This neuron fires on the word “Research,” especially in the phrase “International Agency for Research on Cancer.”

    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
     weapon
    -0.06
    .)↵↵↵↵
    -0.06
    Cele
    -0.06
     Opr
    -0.06
     大阪
    -0.06
    ůsob
    -0.06
     primeira
    -0.06
    (login
    -0.06
    aspect
    -0.06
     їй
    -0.06
    POSITIVE LOGITS
    Resolved
    0.07
    杂
    0.07
    543
    0.07
    _press
    0.06
    	protected
    0.06
    堂
    0.06
    Inflater
    0.06
    /ex
    0.06
    bits
    0.06
    =sum
    0.06
    Activations Density 0.000%

    No Known Activations