© 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. 16872
    Prev
    Next
    INDEX
    Explanations

    historical events related to education and policy establishment

    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
    ahan
    -0.07
    LOUD
    -0.06
    itele
    -0.06
     ens
    -0.06
     adj
    -0.06
     Animalia
    -0.06
     dispro
    -0.06
    ovation
    -0.06
    roduce
    -0.06
    adoo
    -0.06
    POSITIVE LOGITS
    jist
    0.06
    sti
    0.06
     Vide
    0.06
    avic
    0.06
    zig
    0.06
    ynth
    0.06
    otime
    0.06
     Chest
    0.06
     пеÑĢеда
    0.06
     samot
    0.06
    Activations Density 0.004%

    No Known Activations