© 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. 106594
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate frequency or typical occurrences

    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
    æ°
    -0.07
    ä¼į
    -0.07
    ãĥ«ãĥī
    -0.07
    ickey
    -0.07
    _THAT
    -0.07
    malı
    -0.06
    ounge
    -0.06
    asons
    -0.06
    ÏĢα
    -0.06
    à¸ľà¸¥
    -0.06
    POSITIVE LOGITS
     xuyên
    0.11
    -used
    0.09
    ly
    0.09
    -place
    0.08
    ily
    0.08
    wealth
    0.08
    alties
    0.08
    weise
    0.08
    äºİ
    0.08
    /pop
    0.08
    Activations Density 0.013%

    No Known Activations