© 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. 58960
    Prev
    Next
    INDEX
    Explanations

    information and tips related to digital rights and production

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

    Punctuation marks (primarily periods) that signal the end of one content section and the transition to a new paragraph, heading, or topic in informative or instructional text.

    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
    ISTORY
    -0.06
    æĪª
    -0.06
    kla
    -0.06
     village
    -0.06
     ê²Ģ
    -0.06
     trace
    -0.06
    ibur
    -0.06
    appen
    -0.05
    ENCHMARK
    -0.05
    kou
    -0.05
    POSITIVE LOGITS
     tips
    0.16
    tips
    0.14
     Tips
    0.13
    Tips
    0.12
     tip
    0.12
     Tip
    0.11
    .tip
    0.11
    -tip
    0.10
    Tip
    0.10
    tip
    0.10
    Activations Density 0.090%

    No Known Activations