© 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. 29755
    Prev
    Next
    INDEX
    Explanations

    court

    np_max-act · gemini-2.0-flash

    legal terminology and references related to court cases and judicial decisions.

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

    The neuron fires on formal references to the lower court’s decision—words like “district,” “court,” “opinion,” “reasoning,” and “affirm”—highlighting appellate affirmations of the district court’s judgment.

    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
    target
    -0.07
    Ip
    -0.06
    ак
    -0.06
    link
    -0.06
     Lies
    -0.06
    _usec
    -0.06
     riot
    -0.06
    _processed
    -0.06
     otáz
    -0.06
    _year
    -0.06
    POSITIVE LOGITS
     tirelessly
    0.07
    compareTo
    0.07
    สถานท
    0.07
     заболевания
    0.07
     입니다
    0.06
    SignUp
    0.06
     Moines
    0.06
    .rollback
    0.06
    .localtime
    0.06
    *this
    0.06
    Activations Density 0.005%

    No Known Activations