© 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. 71270
    Prev
    Next
    INDEX
    Explanations

    numerical data and metrics related to progress or statistics

    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
    isle
    -0.09
     Pickup
    -0.06
    zan
    -0.06
    eur
    -0.06
     intr
    -0.06
    bj
    -0.05
     therefore
    -0.05
    lem
    -0.05
    ftar
    -0.05
    лен
    -0.05
    POSITIVE LOGITS
     future
    0.16
     plans
    0.14
    future
    0.14
    plans
    0.13
    Future
    0.12
    æľªæĿ¥
    0.12
     Future
    0.12
     upcoming
    0.12
     Plans
    0.12
     forthcoming
    0.11
    Activations Density 0.055%

    No Known Activations