© 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. 27979
    Prev
    Next
    INDEX
    Explanations

    complex mathematical expressions and structures

    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
    ãĤĩãģĨ
    -0.07
    agn
    -0.07
    tingham
    -0.07
    pty
    -0.06
    inkle
    -0.06
    hr
    -0.06
    BOOK
    -0.06
    borough
    -0.06
    {{
    -0.06
    urb
    -0.06
    POSITIVE LOGITS
     ogs
    0.07
    ÐĴС
    0.07
     γεÏģ
    0.07
    INAL
    0.06
    istics
    0.06
    UED
    0.06
    .GroupLayout
    0.06
     Incontri
    0.06
    .updateDynamic
    0.06
    âĻ¡
    0.06
    Activations Density 0.197%

    No Known Activations