© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 1051
    Prev
    Next
    INDEX
    Explanations

    references to Microsoft Office software programs and their features

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

    References to office software applications (e.g., "Word", "Excel"), document formats, and computing tools, often in technical documentation or product descriptions.

    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
    erval
    -0.07
     Ñĥв
    -0.06
    |#
    -0.06
    ime
    -0.06
    ноз
    -0.06
    esh
    -0.06
    èĦ
    -0.06
    ESH
    -0.06
     dem
    -0.06
    684
    -0.06
    POSITIVE LOGITS
     Office
    0.09
    Office
    0.09
    .office
    0.08
    productive
    0.07
     productive
    0.07
    .Office
    0.07
    AndView
    0.07
    argin
    0.07
     productivity
    0.07
    Calibri
    0.07
    Activations Density 0.045%

    No Known Activations