© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 93900
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and definitions

    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
    sla
    -0.06
    ersen
    -0.06
     opposite
    -0.06
     Ear
    -0.06
     Knife
    -0.06
    arena
    -0.06
    OrDefault
    -0.06
    Ear
    -0.06
    grund
    -0.06
    arkin
    -0.06
    POSITIVE LOGITS
     yine
    0.07
     itself
    0.07
     resulting
    0.07
    793
    0.07
     fellow
    0.07
    elsea
    0.06
    оÑĹ
    0.06
     ÑĤоже
    0.06
     another
    0.06
     Demp
    0.06
    Activations Density 0.104%

    No Known Activations