© 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. 57162
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of “Court,” particularly in the phrase “the Court” when referring to the judicial body in case documents.

    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
     Attack
    -0.07
    azole
    -0.07
    (#
    -0.07
     illustrate
    -0.07
    .Unit
    -0.07
    δό
    -0.07
    ephir
    -0.07
     جمعیت
    -0.06
    Lens
    -0.06
     illustrates
    -0.06
    POSITIVE LOGITS
     Gins
    0.08
    ifes
    0.06
     sickness
    0.06
     escalating
    0.06
     zev
    0.06
     Bh
    0.06
    aus
    0.06
     pups
    0.05
     Kendall
    0.05
    原始
    0.05
    Activations Density 0.003%

    No Known Activations