© 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. 57817
    Prev
    Next
    INDEX
    Explanations

    legal cases

    np_max-act · gemini-2.0-flash

    references to legal cases and court decisions.

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

    This neuron activates on the case‐caption metadata—court names, jurisdiction labels, and docket identifiers (e.g. “Super. Ct.,” “Los Angeles County,” case number tokens) in the header.

    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
    pak
    -0.06
    然
    -0.06
    prepend
    -0.06
    iphone
    -0.06
    iễn
    -0.06
    -training
    -0.06
    ymbol
    -0.06
     ​​​
    -0.06
    udent
    -0.06
     walnut
    -0.06
    POSITIVE LOGITS
     qualify
    0.07
     IMapper
    0.07
     stip
    0.06
     Ülke
    0.06
    検
    0.06
    leri
    0.06
     *_
    0.06
     Decay
    0.06
     askeri
    0.06
    ６
    0.06
    Activations Density 0.004%

    No Known Activations