© 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. 58743
    Prev
    Next
    INDEX
    Explanations

    information related to changes or modifications over time

    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
     excell
    -0.07
    çĽijåIJ¬é¡µéĿ¢
    -0.07
    ¶Į
    -0.06
    ordinate
    -0.06
    orks
    -0.06
    root
    -0.06
    ordinated
    -0.06
     bát
    -0.06
    ñana
    -0.06
    ancia
    -0.06
    POSITIVE LOGITS
     recent
    0.09
     modern
    0.09
    modern
    0.08
    recent
    0.07
    Recent
    0.07
     moderne
    0.07
     original
    0.07
     contemporary
    0.07
     Recent
    0.07
    ackbar
    0.06
    Activations Density 0.020%

    No Known Activations