© 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. 119655
    Prev
    Next
    INDEX
    Explanations

    references to methods and practices in various fields

    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
    wig
    -0.09
    ri
    -0.08
    lier
    -0.08
    leigh
    -0.08
    teen
    -0.08
    orian
    -0.07
    rou
    -0.07
    rial
    -0.07
    mand
    -0.07
    imer
    -0.07
    POSITIVE LOGITS
    ically
    0.10
    ologies
    0.10
    ological
    0.09
    ology
    0.09
     latter
    0.08
    ologically
    0.08
    anical
    0.08
    ical
    0.07
    sters
    0.07
    aden
    0.07
    Activations Density 0.011%

    No Known Activations