© 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. 6174
    Prev
    Next
    INDEX
    Explanations

    Circuit

    np_max-act · gemini-2.0-flash

    legal terminology and references to court cases.

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

    The neuron fires on occurrences of the phrase “Fourth Circuit” (i.e. references to the U.S. Court of Appeals for the Fourth Circuit) in legal‐citation text.

    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
    開発
    -0.06
    чя
    -0.06
    啦
    -0.06
    ropol
    -0.06
    }"
    -0.06
     jego
    -0.06
    _LINEAR
    -0.06
    া
    -0.06
     نموده
    -0.06
     sah
    -0.05
    POSITIVE LOGITS
     Cases
    0.08
     tgt
    0.08
     cases
    0.07
    IndexPath
    0.07
     holding
    0.07
    lined
    0.07
     resolving
    0.07
    _arrow
    0.07
    urg
    0.07
    llib
    0.06
    Activations Density 0.001%

    No Known Activations