© 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. 17137
    Prev
    Next
    INDEX
    Explanations

    terms related to programming algorithms and their performance

    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
    ledged
    -0.06
    loit
    -0.06
    BCM
    -0.06
    -addons
    -0.06
    own
    -0.06
    اءات
    -0.06
    .sam
    -0.06
    angent
    -0.06
     country
    -0.06
     dot
    -0.06
    POSITIVE LOGITS
     Distributed
    0.08
    ooter
    0.07
    distributed
    0.07
     stencil
    0.07
     distributed
    0.07
     spills
    0.07
     Davidson
    0.06
    زة
    0.06
     dram
    0.06
     Fluid
    0.06
    Activations Density 0.030%

    No Known Activations