© 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. 76264
    Prev
    Next
    INDEX
    Explanations

    quantitative measurements or statistics

    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
    enu
    -0.08
    ilater
    -0.08
    ENU
    -0.07
    ستگÛĮ
    -0.07
    Äįet
    -0.07
    اذا
    -0.07
    tracts
    -0.07
    pedia
    -0.07
    ÙĪدÙĩ
    -0.07
    Äįek
    -0.07
    POSITIVE LOGITS
     these
    0.13
     this
    0.10
     those
    0.10
    è¿ĻäºĽ
    0.10
     Äijó
    0.09
    these
    0.09
     that
    0.08
    è¿Ļ个
    0.07
     These
    0.07
     of
    0.07
    Activations Density 0.014%

    No Known Activations