© 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. 15-RESID-POST-AA
    11. 84574
    Prev
    Next
    INDEX
    Explanations

    Dates and times

    np_max-act · gemini-2.0-flash

    tokens that are part of timestamps, dates, times, and forum post time/location metadata (e.g., "am/pm", numeric dates, timezones).

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .initialize
    -0.07
     construction
    -0.07
    .setStroke
    -0.06
    	real
    -0.06
    .with
    -0.06
    .sb
    -0.06
    	Public
    -0.06
    	camera
    -0.06
     своей
    -0.06
    .create
    -0.06
    POSITIVE LOGITS
     tä
    0.07
     ForCanBeConvertedToForeach
    0.07
    REV
    0.06
    evity
    0.06
     Sı
    0.06
    liable
    0.06
    険
    0.06
    impact
    0.06
    пе
    0.06
     		↵
    0.06
    Activations Density 0.021%

    No Known Activations