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

    Neuronpedia

    Jacobian LensNEW
    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. 88757
    Prev
    Next
    INDEX
    Explanations

    references to literary works or authors

    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
    estion
    -0.06
     Torch
    -0.06
    aza
    -0.06
    ìĨį
    -0.06
    ween
    -0.06
    ibar
    -0.06
    ÙIJ
    -0.06
    .resolution
    -0.06
     newsp
    -0.06
    APS
    -0.06
    POSITIVE LOGITS
    è²ł
    0.07
     ìĺĪìłķ
    0.07
    MSG
    0.06
    /plugin
    0.06
    edef
    0.06
    .SetText
    0.06
    iram
    0.06
    год
    0.06
    .MSG
    0.06
    adÃŃ
    0.06
    Activations Density 0.028%

    No Known Activations