© 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. 9-LLAMASCOPE-RES-131K
    11. 96407
    Prev
    Next
    INDEX
    Explanations

    references to the transition from analog to digital technology

    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
    uxt
    -0.06
    ergus
    -0.06
    agi
    -0.06
    usercontent
    -0.06
     ac
    -0.06
    оÑĩки
    -0.06
    amina
    -0.06
     unre
    -0.05
     sos
    -0.05
     Osc
    -0.05
    POSITIVE LOGITS
    itti
    0.07
    ingroup
    0.07
    (æĹ¥
    0.07
    à¥Ģà¤ķरण
    0.07
    IGNED
    0.07
    ropolis
    0.07
    ted
    0.07
    íĮħ
    0.07
    etro
    0.07
    bum
    0.07
    Activations Density 0.004%

    No Known Activations