© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 4366
    Prev
    Next
    INDEX
    Explanations

    adverbs and adjectives that describe various fields of science and their impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    तम
    -0.08
    est
    -0.07
    itou
    -0.07
    ably
    -0.07
    leftright
    -0.07
    ãĤ¹ãĥĨãĤ£
    -0.07
    ä¸Ķ
    -0.07
    erez
    -0.07
    ables
    -0.06
    mouseenter
    -0.06
    POSITIVE LOGITS
     speaking
    0.07
    neutral
    0.07
     neutral
    0.06
     savvy
    0.06
    adr
    0.06
    /social
    0.06
    esor
    0.06
    sound
    0.06
    .sound
    0.06
    ép
    0.06
    Activations Density 0.027%

    No Known Activations