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

    Neuronpedia

    Jacobian LensNEW
    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. 57222
    Prev
    Next
    INDEX
    Explanations

    safe

    np_max-act · gemini-2.0-flash

    The neuron activates on terms related to thread‐safety and concurrency constructs (e.g. “thread‐safe,” “Concurrent,” “sync,” etc.).

    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
    /util
    -0.06
    scene
    -0.06
     Weinstein
    -0.06
    ``↵
    -0.06
    named
    -0.06
    Device
    -0.06
    .*(
    -0.06
    KeyPressed
    -0.06
     educ
    -0.06
    typ
    -0.06
    POSITIVE LOGITS
     вспом
    0.07
    vanced
    0.07
     января
    0.07
     toho
    0.07
    と思う
    0.07
     podařilo
    0.07
    Signal
    0.07
    UPI
    0.07
    otton
    0.06
    commerce
    0.06
    Activations Density 0.005%

    No Known Activations