© 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. 15982
    Prev
    Next
    INDEX
    Explanations

    terms related to a specific organization or entity

    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
    uke
    -0.07
     Wein
    -0.06
    aber
    -0.06
    luluk
    -0.06
    åģ¶
    -0.06
    alf
    -0.06
    perPage
    -0.06
    ÏĥÏĦÏĮ
    -0.06
    adelphia
    -0.06
    uja
    -0.06
    POSITIVE LOGITS
    ding
    0.09
    ing
    0.08
    anning
    0.08
    bing
    0.08
    ving
    0.08
    TING
    0.08
    ating
    0.07
    king
    0.07
    инг
    0.07
    ting
    0.07
    Activations Density 0.133%

    No Known Activations