© 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. 59781
    Prev
    Next
    INDEX
    Explanations

    references to the number of episodes in a series

    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
    endez
    -0.06
    primitive
    -0.06
    omp
    -0.06
    edral
    -0.06
    ói
    -0.06
    communic
    -0.06
    _PRINT
    -0.06
    лим
    -0.06
    etat
    -0.06
     Griffin
    -0.06
    POSITIVE LOGITS
    enberg
    0.07
    indrome
    0.07
    AGO
    0.06
     Cod
    0.06
    \widgets
    0.06
     çIJ
    0.06
    Cod
    0.06
    ANGUAGE
    0.06
    iest
    0.06
    ighborhood
    0.06
    Activations Density 0.000%

    No Known Activations