© 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. 17-LLAMASCOPE-RES-131K
    11. 124995
    Prev
    Next
    INDEX
    Explanations

    references to community issues and related initiatives

    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
    enty
    -0.08
    .fp
    -0.08
    ateria
    -0.07
    æ¢
    -0.07
    .camel
    -0.06
     ÙħÙģ
    -0.06
    wnd
    -0.06
    ulur
    -0.06
    ãĤ¤ãĥĦ
    -0.06
    instant
    -0.06
    POSITIVE LOGITS
    alink
    0.08
     expansion
    0.06
    obra
    0.06
    ìłĢ
    0.06
     expansions
    0.06
     affordable
    0.06
    ds
    0.06
     locally
    0.06
    á»ijt
    0.06
    engo
    0.06
    Activations Density 0.007%

    No Known Activations