© 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. 123971
    Prev
    Next
    INDEX
    Explanations

    phrases that highlight novel research findings and first-time observations in scientific studies

    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
    á»ijt
    -0.07
     klu
    -0.06
     prostitu
    -0.06
    ãĥĥãĥĦ
    -0.06
     Phen
    -0.06
     Moreno
    -0.06
     decks
    -0.06
     último
    -0.06
     poil
    -0.06
    uddle
    -0.06
    POSITIVE LOGITS
     published
    0.07
     reported
    0.07
    attempt
    0.07
    reported
    0.07
    ield
    0.07
    ureen
    0.07
    aptured
    0.06
     report
    0.06
    estone
    0.06
     study
    0.06
    Activations Density 0.013%

    No Known Activations