© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 126466
    Prev
    Next
    INDEX
    Explanations

    elements related to programming and technical error handling

    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
    quires
    -0.07
     /*#__
    -0.07
    mal
    -0.06
    ardy
    -0.06
    ãĤ«ãĥĨãĤ´ãĥª
    -0.06
    ãĥ¼ãĥł
    -0.06
    wan
    -0.06
    лÑİб
    -0.06
    oyer
    -0.06
    agle
    -0.06
    POSITIVE LOGITS
    رÙĪÛĮ
    0.07
    ãĥ¼ãĥĩ
    0.06
    reso
    0.06
    askell
    0.06
    ANDLE
    0.06
    ober
    0.06
    /../
    0.06
    ONGL
    0.06
    affer
    0.05
    upon
    0.05
    Activations Density 0.013%

    No Known Activations