© 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. 78069
    Prev
    Next
    INDEX
    Explanations

    references to notable historical events or figures

    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
    .ops
    -0.08
     slož
    -0.08
     -*-č↵
    -0.08
    ç·
    -0.08
    anka
    -0.08
    -д
    -0.07
    áf
    -0.07
    лагод
    -0.07
     {{--<
    -0.07
    senal
    -0.07
    POSITIVE LOGITS
     whom
    0.08
     others
    0.08
     crush
    0.07
     him
    0.07
     John
    0.07
     who
    0.06
    dr
    0.06
     Ray
    0.06
     guy
    0.06
    543
    0.06
    Activations Density 0.101%

    No Known Activations