© 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. 110791
    Prev
    Next
    INDEX
    Explanations

    control

    np_max-act · gemini-2.0-flash

    concepts related to advanced control theories and their applications to dynamic systems.

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

    The neuron activates on technical terms referring to control theory and cybernetics.

    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
     Prostit
    -0.07
    ули
    -0.07
    čel
    -0.06
    ani
    -0.06
    oric
    -0.06
     mereka
    -0.06
     meny
    -0.06
    触
    -0.06
    วก
    -0.06
    리로
    -0.06
    POSITIVE LOGITS
    øre
    0.07
    .hashCode
    0.07
    ipel
    0.06
    -stage
    0.06
     GA
    0.06
    픽
    0.06
    (cont
    0.06
    itimate
    0.06
     BUSINESS
    0.06
    шее
    0.06
    Activations Density 0.017%

    No Known Activations