© 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. 41144
    Prev
    Next
    INDEX
    Explanations

    mentions of "desktop" in various contexts

    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
    باد
    -0.08
    IGH
    -0.08
    коÑĤ
    -0.07
    emark
    -0.07
    ël
    -0.07
    igh
    -0.07
    brick
    -0.07
    inkel
    -0.06
    ibles
    -0.06
    ãĤ¶ãĥ¼
    -0.06
    POSITIVE LOGITS
    /table
    0.09
    /Table
    0.08
    /mobile
    0.08
    s
    0.07
    shire
    0.07
    ized
    0.07
    ornado
    0.07
    pag
    0.06
    -scale
    0.06
    -sized
    0.06
    Activations Density 0.003%

    No Known Activations