© 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. 17-LLAMASCOPE-RES-131K
    11. 89041
    Prev
    Next
    INDEX
    Explanations

    comments on the complexity and readability of code

    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
    ležit
    -0.07
    rp
    -0.06
     Morton
    -0.06
     иÑģÑħод
    -0.06
    ich
    -0.06
     Profit
    -0.06
    _clause
    -0.06
    trie
    -0.06
     Impossible
    -0.06
    /render
    -0.06
    POSITIVE LOGITS
    วà¸Ķ
    0.07
    vida
    0.07
    olson
    0.07
     solution
    0.07
    ä¸įå®ī
    0.07
     solutions
    0.07
    ÏħÏĩ
    0.06
     satisfactory
    0.06
     Solution
    0.06
    èĢ
    0.06
    Activations Density 0.015%

    No Known Activations