© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 18152
    Prev
    Next
    INDEX
    Explanations

    powerpoint

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of PowerPoint/PPT presentations (references to creating, showing, or discussing slides/presentations).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _FUNC
    -0.08
    -money
    -0.06
     disdain
    -0.06
     мала
    -0.06
     them
    -0.06
     modules
    -0.06
    tolower
    -0.06
    ():
↵
    -0.06
     numbers
    -0.06
     pragmatic
    -0.06
    POSITIVE LOGITS
     PowerPoint
    0.12
    フト
    0.07
    τερ
    0.07
    >R
    0.07
    scheduled
    0.06
     pj
    0.06
    لیل
    0.06
    .crt
    0.06
     Bryce
    0.06
    rd
    0.06
    Activations Density 0.002%

    No Known Activations