© 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. 83431
    Prev
    Next
    INDEX
    Explanations

    content related to technology and trends

    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
    .outputs
    -0.07
    λοÏĤ
    -0.07
    Commerce
    -0.07
    ãĥ¼ãĤ¯
    -0.06
    ï¼ľ
    -0.06
     mand
    -0.06
    DEX
    -0.06
    igue
    -0.06
    اباÙĨ
    -0.06
     ï¼ľ
    -0.06
    POSITIVE LOGITS
     news
    0.10
    -news
    0.08
    news
    0.08
     News
    0.08
     NEWS
    0.07
    mpar
    0.07
    ViewChild
    0.07
     trends
    0.07
    asiswa
    0.07
    vens
    0.07
    Activations Density 0.021%

    No Known Activations