© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 125121
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "involution."

    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
    ioxide
    -0.09
    ypse
    -0.08
    theid
    -0.07
    ickness
    -0.07
    tempts
    -0.07
    quals
    -0.07
    ãģ°
    -0.07
    ogui
    -0.07
    INESS
    -0.07
    -vous
    -0.07
    POSITIVE LOGITS
    s
    0.08
    i
    0.07
    igo
    0.07
    sut
    0.07
    uesto
    0.07
    mar
    0.06
    ri
    0.06
    uman
    0.06
    usz
    0.06
    urb
    0.06
    Activations Density 0.109%

    No Known Activations