© 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. 9-LLAMASCOPE-RES-131K
    11. 94498
    Prev
    Next
    INDEX
    Explanations

    terms related to solar wind and its effects on Earth's magnetosphere

    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
    èĺ
    -0.07
    ities
    -0.07
    assy
    -0.07
    maj
    -0.07
    borough
    -0.07
    atu
    -0.07
    θι
    -0.07
    zell
    -0.06
    _pipeline
    -0.06
    mbH
    -0.06
    POSITIVE LOGITS
    ift
    0.06
    gly
    0.06
     th
    0.06
    ach
    0.05
     Bern
    0.05
    .crypto
    0.05
     Morton
    0.05
     ëŁ
    0.05
    ernote
    0.05
     Fore
    0.05
    Activations Density 0.008%

    No Known Activations