© 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. 15-LLAMASCOPE-RES-131K
    11. 588
    Prev
    Next
    INDEX
    Explanations

    technical details and error messages from programming languages, specifically Java

    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
    mÃŃt
    -0.09
    окон
    -0.08
    .Dimension
    -0.07
    æİ¢
    -0.07
    >NN
    -0.07
     rencont
    -0.07
    ãģĭãĤı
    -0.07
    oslav
    -0.07
    tero
    -0.07
    -Semit
    -0.07
    POSITIVE LOGITS
     {{{
    0.06
     ar
    0.06
     ex
    0.06
    Clo
    0.05
     error
    0.05
     released
    0.05
     Ross
    0.05
     ch
    0.05
    shore
    0.05
     Controls
    0.05
    Activations Density 0.001%

    No Known Activations