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. 12922
    Prev
    Next
    INDEX
    Explanations

    legal citations

    np_max-act · gemini-2.0-flash

    This neuron detects the formal courtroom document headers and docket identifiers (case numbers, court names, dates, and similar metadata).

    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
     důvodu
    -0.06
    '"
    -0.06
    347
    -0.06
    =',
    -0.06
     알아
    -0.06
     bölüm
    -0.06
     некотор
    -0.06
     PUT
    -0.06
     CH
    -0.06
     {}",
    -0.06
    POSITIVE LOGITS
     orm
    0.06
     atas
    0.06
     retained
    0.06
     tener
    0.06
    经
    0.06
    _HAS
    0.06
     Riot
    0.06
    روع
    0.06
    ahat
    0.06
     Sweat
    0.06
    Activations Density 0.002%

    No Known Activations