© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 68939
    Prev
    Next
    INDEX
    Explanations

    vest

    np_max-act · gemini-2.0-flash

    This neuron activates on terms related to vesting (e.g., “vest,” “vesting”) in compensation or equity contexts.

    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
    .download
    -0.07
    _allocation
    -0.07
    _numbers
    -0.07
    _utils
    -0.07
     çalışan
    -0.07
    _FAILED
    -0.07
    _commands
    -0.07
     cleanup
    -0.07
     MACHINE
    -0.07
    _IOCTL
    -0.06
    POSITIVE LOGITS
     Vest
    0.11
     vestib
    0.09
     vested
    0.09
     vest
    0.08
    hest
    0.08
    st
    0.07
     vests
    0.07
    vf
    0.07
    vest
    0.07
    est
    0.07
    Activations Density 0.003%

    No Known Activations