© 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. 28535
    Prev
    Next
    INDEX
    Explanations

    mentions of directories related to services or resources

    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
    vise
    -0.08
    omba
    -0.08
    ovo
    -0.08
    во
    -0.07
    hawks
    -0.07
    HeaderText
    -0.07
    .swt
    -0.07
    ãģ«ãģĹãģ¦
    -0.07
    <quote
    -0.07
    ä¿Ĺ
    -0.07
    POSITIVE LOGITS
    ton
    0.07
    ix
    0.07
     ActionTypes
    0.06
    occo
    0.06
    894
    0.06
    TON
    0.06
    iek
    0.06
    SD
    0.06
    360
    0.06
    0.06
    Activations Density 0.002%

    No Known Activations