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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 9502
    Prev
    Next
    INDEX
    Explanations

    fit

    np_max-act · gemini-2.0-flash

    This neuron responds to mentions of a candidate’s suitability—specifically phrases about finding a “good fit” (e.g., “candidates … who are a good fit for our company culture”).

    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
     oud
    -0.07
     trolls
    -0.07
     области
    -0.06
     onload
    -0.06
    кі
    -0.06
     hatte
    -0.06
    .endswith
    -0.06
     کرد
    -0.06
     grit
    -0.06
     heard
    -0.06
    POSITIVE LOGITS
    routing
    0.06
    ...
    0.06
     UserController
    0.06
    /on
    0.06
    nEnter
    0.06
     Slav
    0.06
    ",'
    0.06
     Luc
    0.06
    @Module
    0.06
     stump
    0.06
    Activations Density 0.035%

    No Known Activations