© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 12663
    Prev
    Next
    INDEX
    Explanations

    JNICALL

    np_max-act · gemini-2.0-flash

    code related to Java Native Interface (JNI) implementations.

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

    The neuron fires on JNI native‐method declarations, i.e. the “JNICALL” token in C function signatures.

    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
    indic
    -0.07
     Nora
    -0.06
     Zar
    -0.06
    arding
    -0.06
    .stats
    -0.06
     QPoint
    -0.06
    pl
    -0.06
     stealth
    -0.06
    :>
    -0.06
    (filepath
    -0.06
    POSITIVE LOGITS
     JNICALL
    0.09
     SIMPLE
    0.06
     glor
    0.06
     bola
    0.06
    grunt
    0.06
    굴
    0.06
     Stokes
    0.06
    etest
    0.06
     initialise
    0.06
     adversely
    0.06
    Activations Density 0.000%

    No Known Activations