© 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 EvalsExportsinterp-engineNEWAPI 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. 73065
    Prev
    Next
    INDEX
    Explanations

    references to awards and honors associated with the Soviet Union

    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
     Gül
    -0.07
    seau
    -0.07
    amac
    -0.07
    bole
    -0.07
    ignon
    -0.07
    Lifecycle
    -0.07
     Sunder
    -0.07
     conservative
    -0.07
    ngen
    -0.07
    æ¢
    -0.07
    POSITIVE LOGITS
     workers
    0.08
     Workers
    0.07
     worker
    0.07
     Worker
    0.07
     prolet
    0.07
    éĻµ
    0.07
     Banner
    0.07
    worker
    0.07
    workers
    0.06
    -worker
    0.06
    Activations Density 0.015%

    No Known Activations