© 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. 83453
    Prev
    Next
    INDEX
    Explanations

    references to metrics or statistical data

    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
    имв
    -0.08
    olest
    -0.07
    окон
    -0.07
    ledon
    -0.07
    tero
    -0.07
    aphael
    -0.07
    tember
    -0.07
    rote
    -0.07
    chia
    -0.07
    rone
    -0.07
    POSITIVE LOGITS
    ï¸ı
    0.10
    οÏĤ
    0.07
    âĢ²
    0.06
    -way
    0.06
    ê°ľë¥¼
    0.06
    ToOne
    0.06
    wstring
    0.06
    ê°ľ
    0.06
    -го
    0.06
    ileri
    0.06
    Activations Density 0.071%

    No Known Activations