© 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 EvalsExportsinterp-engineNEWAPI 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. 72429
    Prev
    Next
    INDEX
    Explanations

    references to additional content or sources in a document

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

    Navigation or continuation markers at the end of article excerpts that prompt readers to access additional 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
    iken
    -0.07
    -Token
    -0.06
    ocket
    -0.06
    ilian
    -0.06
    chio
    -0.06
    iker
    -0.06
    uns
    -0.06
    aniel
    -0.06
     Mun
    -0.06
     lam
    -0.06
    POSITIVE LOGITS
    uraa
    0.08
    zell
    0.07
    _outline
    0.07
    *>*
    0.07
    iert
    0.07
    ayed
    0.07
    STRU
    0.06
    unts
    0.06
    arLayout
    0.06
    iembre
    0.06
    Activations Density 0.517%

    No Known Activations