© 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. 58241
    Prev
    Next
    INDEX
    Explanations

    references to filtering and managing data for easier access and retrieval

    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
    erm
    -0.07
     Kos
    -0.07
    /Table
    -0.07
    vig
    -0.07
     somehow
    -0.06
     something
    -0.06
    ignum
    -0.06
    ekli
    -0.06
     Kes
    -0.06
    etrofit
    -0.06
    POSITIVE LOGITS
    аÑĤкÑĥ
    0.06
    aved
    0.06
     interpreter
    0.06
    hind
    0.06
    ='<?
    0.06
    .nom
    0.06
    ufs
    0.06
     hi
    0.06
    Mozilla
    0.06
    ÑĢави
    0.06
    Activations Density 0.006%

    No Known Activations