© 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. 4769
    Prev
    Next
    INDEX
    Explanations

    LaTeX commands related to figures and tables in a document

    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
    efd
    -0.08
    лÑıв
    -0.08
    uggy
    -0.07
    atron
    -0.07
    код
    -0.07
    ï½į
    -0.07
    esy
    -0.07
    å¹¹ç·ļ
    -0.07
    course
    -0.07
    acz
    -0.07
    POSITIVE LOGITS
    -wide
    0.08
    aver
    0.07
    avers
    0.07
    ieg
    0.06
    ìļ±
    0.06
    -scale
    0.06
    ischer
    0.06
    å¹
    0.06
    lix
    0.06
    .org
    0.06
    Activations Density 0.004%

    No Known Activations