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

    Neuronpedia

    Jacobian LensNEW
    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. 103543
    Prev
    Next
    INDEX
    Explanations

    question and answer pairs

    np_max-act · gemini-2.0-flash

    The neuron fires on reported-speech attributions—instances where the author notes asking, being told, or otherwise receiving information from a source.

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

    queries related to educational policy and historical context.

    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
     punching
    -0.08
     :
    -0.08
    	h
    -0.08
    iets
    -0.07
    _principal
    -0.07
     forum
    -0.07
    closed
    -0.06
     Her
    -0.06
    ↵				↵
    -0.06
    (message
    -0.06
    POSITIVE LOGITS
     Pry
    0.06
     Zukunft
    0.06
    .policy
    0.06
     Chill
    0.06
    krét
    0.06
     آدم
    0.06
    olesale
    0.06
     Zion
    0.06
    aar
    0.06
     zIndex
    0.06
    Activations Density 0.024%

    No Known Activations