© 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 EvalsExportsinterp-engineNEWAPI 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. 57891
    Prev
    Next
    INDEX
    Explanations

    Nash equilibrium

    np_max-act · gemini-2.0-flash

    This neuron never activates—i.e. it responds to no tokens (it’s essentially a “dead” neuron).

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

    terms related to multi-objective optimization and Pareto efficiency.

    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
     problème
    -0.07
    Tour
    -0.07
     Visit
    -0.07
    $$$$
    -0.06
    otyp
    -0.06
    onaut
    -0.06
     Rubber
    -0.06
     eyewitness
    -0.06
    unsch
    -0.06
    ru
    -0.06
    POSITIVE LOGITS
     перем
    0.07
    rescia
    0.07
     clinically
    0.07
    노출
    0.06
     sağlam
    0.06
    真正
    0.06
     magnesium
    0.06
    岸
    0.06
    togroup
    0.06
     зовсім
    0.06
    Activations Density 0.003%

    No Known Activations