© 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. 54365
    Prev
    Next
    INDEX
    Explanations

    urb

    np_max-act · gemini-2.0-flash

    discussions related to gauge theories and their applications in high-energy physics.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron chiefly responds to occurrences of the word “strong” (and its derivative “strongly”) in the context of describing the strong interaction or strongly correlated gluons.

    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
     CLOCK
    -0.08
    _pages
    -0.07
     aspirations
    -0.07
     userType
    -0.07
    loc
    -0.07
    	pstmt
    -0.07
    .position
    -0.07
     Raj
    -0.07
     bricks
    -0.07
    िजन
    -0.06
    POSITIVE LOGITS
     STATS
    0.07
     Да
    0.07
    „To
    0.06
     Hunts
    0.06
     CONFIG
    0.06
    ","
    0.06
     春
    0.06
    ？」
    0.06
     المو
    0.06
    .rstrip
    0.06
    Activations Density 0.002%

    No Known Activations