© 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 EvalsExportsAPI 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. 29134
    Prev
    Next
    INDEX
    Explanations

    numerical data and percentages

    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
    aimassage
    -0.09
    izik
    -0.08
    otionEvent
    -0.07
     ฿
    -0.06
    azing
    -0.06
    ácil
    -0.06
    ruz
    -0.06
    PKG
    -0.06
    373
    -0.06
    addock
    -0.06
    POSITIVE LOGITS
    uni
    0.08
    ile
    0.07
    ensi
    0.07
    aul
    0.06
    oksen
    0.06
    stream
    0.06
    iqu
    0.06
     Tre
    0.06
    edo
    0.06
    ar
    0.06
    Activations Density 0.009%

    No Known Activations