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

    Neuronpedia

    Jacobian LensNEW
    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. 84390
    Prev
    Next
    INDEX
    Explanations

    references to music and its categorization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Specific noun phrases representing distinct concepts, products, or categories that would typically be found in informational, classificatory, or catalog-style content.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    /Dk
    -0.07
     ==============================================================
    -0.07
    abwe
    -0.06
    .hs
    -0.06
    chio
    -0.06
    alborg
    -0.06
    Hung
    -0.06
    &id
    -0.06
    ordan
    -0.06
    uries
    -0.06
    POSITIVE LOGITS
    ToolStripMenuItem
    0.08
    DataGridViewTextBoxColumn
    0.08
     Archives
    0.08
     Shields
    0.07
    ↵
    0.06
    .jpg
    0.06
    .JPG
    0.06
    orses
    0.06
     Murray
    0.06
    žil
    0.06
    Activations Density 0.185%

    No Known Activations