© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 121234
    Prev
    Next
    INDEX
    Explanations

    references to specific characters and their interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Character names in narrative fiction that serve as perspective anchors, typically appearing at paragraph beginnings and followed by the character's actions, thoughts, or dialogue.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    blink
    -0.08
    èĺ
    -0.07
     hiss
    -0.07
    Ø·ÙĬ
    -0.07
    -REAL
    -0.06
    slick
    -0.06
    Knife
    -0.06
    onis
    -0.06
     xúc
    -0.06
    éli
    -0.06
    POSITIVE LOGITS
    _exceptions
    0.07
     aka
    0.07
     masses
    0.06
    licht
    0.06
     reply
    0.06
     convers
    0.06
     gl
    0.06
     tens
    0.06
     meanwhile
    0.06
     mass
    0.06
    Activations Density 0.080%

    No Known Activations