Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 129469
    Prev
    Next
    INDEX
    Explanations

    District

    np_max-act · gemini-2.0-flash

    legal terminology related to court cases and judgments.

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

    The neuron detects occurrences of court jurisdiction citations, e.g. “District Court of Appeal of Florida, Third District.”

    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
    getC
    -0.06
     ủy
    -0.06
     Máy
    -0.06
    _chr
    -0.06
     대답
    -0.06
    _two
    -0.06
     expl
    -0.05
    ;\
    -0.05
     <?
    -0.05
    Say
    -0.05
    POSITIVE LOGITS
     ธ
    0.07
     �
    0.07
    758
    0.07
    _digest
    0.06
    vetica
    0.06
     Arizona
    0.06
     brasile
    0.06
     Hunts
    0.06
    _Begin
    0.06
    avez
    0.06
    Activations Density 0.000%

    No Known Activations