© 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. 15500
    Prev
    Next
    INDEX
    Explanations

    syntax structures and control flow elements commonly used in programming

    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
     telah
    -0.08
     Verd
    -0.06
    jan
    -0.06
     has
    -0.06
    OLS
    -0.06
    lanmÄ±ÅŁtır
    -0.06
    uels
    -0.06
    Vert
    -0.06
    Verb
    -0.06
    ardon
    -0.06
    POSITIVE LOGITS
     Doch
    0.06
    palette
    0.06
    wa
    0.06
    noinspection
    0.06
    анка
    0.06
    çĭIJ
    0.06
    ]';↵
    0.06
    æ£
    0.06
     Wa
    0.06
     TU
    0.06
    Activations Density 0.021%

    No Known Activations