© 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. 26490
    Prev
    Next
    INDEX
    Explanations

    numerical specifications and comparisons related to technology or gadgets

    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
    874
    -0.07
    872
    -0.06
    platz
    -0.06
    presso
    -0.06
    986
    -0.06
    bate
    -0.05
    774
    -0.05
     inform
    -0.05
     Schwartz
    -0.05
    íĹĮ
    -0.05
    POSITIVE LOGITS
    aab
    0.07
     ä¹Ŀ
    0.07
    _Clear
    0.07
    ÐĿаÑģ
    0.07
    Æ°á»Ľng
    0.07
    Ｖ
    0.07
    ãĢ
    0.07
     nackte
    0.07
    नल
    0.07
    estroy
    0.07
    Activations Density 0.015%

    No Known Activations