© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 29970
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to programming and computer graphics

    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
    esis
    -0.07
    ional
    -0.06
    ensively
    -0.06
    ument
    -0.06
    -turned
    -0.06
    ylim
    -0.06
    uish
    -0.06
    merce
    -0.06
     Bis
    -0.06
    .LayoutParams
    -0.05
    POSITIVE LOGITS
    ãĥ
    0.08
    (?:
    0.08
    STYPE
    0.08
    ãĤ¿ãĥ¼
    0.07
    ÑĪе
    0.07
    Å®
    0.07
    ichert
    0.07
    isman
    0.07
     Typeface
    0.07
    anh
    0.07
    Activations Density 0.045%

    No Known Activations