© 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. 39741
    Prev
    Next
    INDEX
    Explanations

    references to dice and rolling mechanics

    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
    Bracket
    -0.07
     Bracket
    -0.07
    bars
    -0.06
    slash
    -0.06
    wich
    -0.06
     sor
    -0.06
    ãĥĹãĥ©
    -0.06
     optical
    -0.06
    witch
    -0.06
     spectacle
    -0.06
    POSITIVE LOGITS
     dice
    0.09
    dice
    0.08
    axter
    0.08
     Dice
    0.08
    spinner
    0.08
    íĨłíĨł
    0.08
    aley
    0.08
     toss
    0.08
    -roll
    0.07
     spinner
    0.07
    Activations Density 0.014%

    No Known Activations