© 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. 9-LLAMASCOPE-RES-131K
    11. 94757
    Prev
    Next
    INDEX
    Explanations

    references to SQL and related database concepts

    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
    uir
    -0.08
    jes
    -0.07
    eker
    -0.07
    keh
    -0.07
    istrovstvÃŃ
    -0.07
    nbsp
    -0.07
    acles
    -0.07
     mau
    -0.07
    lify
    -0.07
    agus
    -0.07
    POSITIVE LOGITS
    ten
    0.08
    ãĤ·ãĥ£
    0.07
    nection
    0.07
    ayout
    0.07
    gnore
    0.07
    anity
    0.07
    Sharper
    0.07
    ans
    0.07
    ander
    0.07
    à¸ģ
    0.06
    Activations Density 0.008%

    No Known Activations