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

    Neuronpedia

    Jacobian LensNEW
    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. 15-RESID-POST-AA
    11. 35084
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    places in text where a sentence is ending and a new one is beginning, particularly with strong activation on periods followed by capitalized words.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @andyrdt
    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
    大全
    -0.07
     MySQL
    -0.07
     execute
    -0.07
    670
    -0.07
     sensor
    -0.06
    textContent
    -0.06
    Checksum
    -0.06
    .annotate
    -0.06
    :animated
    -0.06
     remained
    -0.06
    POSITIVE LOGITS
     Glasgow
    0.06
    Vel
    0.06
    emb
    0.06
     Rockefeller
    0.06
    Ef
    0.06
    PopupMenu
    0.06
     sitios
    0.06
     watermark
    0.06
     nackte
    0.06
    ummings
    0.06
    Activations Density 1.458%

    No Known Activations