© 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. 17190
    Prev
    Next
    INDEX
    Explanations

    references to gaming mechanics and features

    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
     excer
    -0.07
    jezd
    -0.07
    ockey
    -0.07
    ãĥ³ãĥķ
    -0.07
     sez
    -0.07
    ruba
    -0.07
     eks
    -0.07
    oucher
    -0.07
     знов
    -0.07
    Æ°Æ¡
    -0.07
    POSITIVE LOGITS
     Erot
    0.07
    lier
    0.07
     Hamp
    0.06
    ánd
    0.06
    ÐĤ
    0.06
    bout
    0.06
     suff
    0.06
    arda
    0.06
    Ñijн
    0.05
    odos
    0.05
    Activations Density 0.132%

    No Known Activations