© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 4401
    Prev
    Next
    INDEX
    Explanations

    references to companies and business entities

    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
    -speaking
    -0.08
    utom
    -0.07
    ìĦľëĬĶ
    -0.07
    pine
    -0.07
    most
    -0.07
    ÄĻ
    -0.07
    onn
    -0.07
    lej
    -0.07
    embr
    -0.07
    angi
    -0.07
    POSITIVE LOGITS
    wide
    0.14
    -wide
    0.10
    ัà¸Ĺ
    0.08
    -client
    0.08
    åĵ¡
    0.07
    /people
    0.07
    hood
    0.07
    children
    0.07
     matriz
    0.07
    -owned
    0.07
    Activations Density 0.050%

    No Known Activations