© 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. 94504
    Prev
    Next
    INDEX
    Explanations

    elements related to database operations in code

    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
     Bomb
    -0.07
    ovah
    -0.06
    778
    -0.06
     Evel
    -0.06
    729
    -0.06
     overdue
    -0.06
    431
    -0.06
    861
    -0.06
    apel
    -0.05
    279
    -0.05
    POSITIVE LOGITS
    lez
    0.07
    _Params
    0.07
    Mex
    0.07
    ijken
    0.07
    UDGE
    0.07
     NONINFRINGEMENT
    0.07
    Extensions
    0.07
    خصÙĪص
    0.06
    اÙħÙĩ
    0.06
    .fac
    0.06
    Activations Density 0.002%

    No Known Activations