© 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. 5-LLAMASCOPE-RES-131K
    11. 125475
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notations

    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
    ostel
    -0.07
     ******************************************************************************↵
    -0.07
    翼
    -0.07
    ÅĻ
    -0.06
     medio
    -0.06
    NX
    -0.06
    ئة
    -0.06
    µľ
    -0.06
    cab
    -0.06
    _fatal
    -0.06
    POSITIVE LOGITS
    alet
    0.07
    usc
    0.07
    nez
    0.06
     Baz
    0.06
    AMB
    0.06
    intree
    0.06
    775
    0.06
    erer
    0.06
     Mill
    0.06
    293
    0.06
    Activations Density 0.027%

    No Known Activations