© 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. 129627
    Prev
    Next
    INDEX
    Explanations

    measuring success and progress

    np_max-act · gemini-2.0-flash

    This neuron activates on words and phrases about measuring, tracking, or evaluating outcomes—e.g., metrics, effectiveness, success, progress.

    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
     repeatedly
    -0.07
     implicitly
    -0.06
     breve
    -0.06
    ysz
    -0.06
     shr
    -0.06
     adolescent
    -0.06
     رف
    -0.06
    _bot
    -0.06
     Garrison
    -0.06
     Signing
    -0.06
    POSITIVE LOGITS
    (number
    0.07
     phúc
    0.07
    čních
    0.07
    좌
    0.06
    paralleled
    0.06
     nomine
    0.06
    ційна
    0.06
     relics
    0.06
     handling
    0.06
     Agencies
    0.06
    Activations Density 0.041%

    No Known Activations