© 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. 14140
    Prev
    Next
    INDEX
    Explanations

    between

    np_max-act · gemini-2.0-flash

    This neuron detects the comparative question pattern, especially the phrase “difference between” when asking how two things differ.

    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
    Uri
    -0.07
     Austral
    -0.06
     JText
    -0.06
    Volumes
    -0.06
    俄
    -0.06
     دادن
    -0.06
     lobby
    -0.06
     astr
    -0.06
    館
    -0.06
    Ep
    -0.06
    POSITIVE LOGITS
    !!!↵
    0.08
    .cat
    0.07
    -water
    0.07
     repost
    0.07
     rozdíl
    0.06
    !!↵
    0.06
    ***
    0.06
     DDS
    0.06
     přem
    0.06
     về
    0.06
    Activations Density 0.017%

    No Known Activations