© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 40077
    Prev
    Next
    INDEX
    Explanations

    references to specific products and their characteristics

    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
    995
    -0.07
    essler
    -0.07
    onga
    -0.06
    ØŃ
    -0.06
    вай
    -0.06
    385
    -0.06
     Barg
    -0.06
    Ùijر
    -0.06
    387
    -0.06
    acob
    -0.06
    POSITIVE LOGITS
     ÙĩÙħÚĨÙĨÛĮÙĨ
    0.08
    istrovstvÃŃ
    0.07
     verg
    0.07
    eer
    0.07
    mach
    0.06
    íļĮìĿĺ
    0.06
    aterangepicker
    0.06
    ekce
    0.06
    706
    0.06
    olina
    0.06
    Activations Density 0.014%

    No Known Activations