© 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. 71658
    Prev
    Next
    INDEX
    Explanations

    phrases indicating functionality or issues related to technology and devices

    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
    ãĥĥ
    -0.07
    Ðĩ
    -0.07
    /sdk
    -0.07
    luet
    -0.06
    ÃĸL
    -0.06
    (nullable
    -0.06
    rollo
    -0.06
    ãĥįãĥ«
    -0.06
    ByUrl
    -0.06
    ubbo
    -0.06
    POSITIVE LOGITS
    LAG
    0.07
     gar
    0.07
     gray
    0.06
    addock
    0.06
     seems
    0.06
     seemed
    0.06
     seem
    0.06
    BOOT
    0.06
    atel
    0.06
    iaÅĤ
    0.06
    Activations Density 0.034%

    No Known Activations