© 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. 89173
    Prev
    Next
    INDEX
    Explanations

    references to population and demographic metrics

    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
    ï¸ı
    -0.08
    born
    -0.07
    nown
    -0.07
    san
    -0.07
    Ù
    -0.07
    ing
    -0.07
    ig
    -0.07
    ling
    -0.07
    sse
    -0.06
    urer
    -0.06
    POSITIVE LOGITS
    ally
    0.10
    oucher
    0.09
    /Area
    0.08
    iyon
    0.08
    /world
    0.08
    UnderTest
    0.08
    alist
    0.08
    wide
    0.07
     ---------------------------------------------------------------------------↵
    0.07
    als
    0.07
    Activations Density 0.013%

    No Known Activations