© 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. 128081
    Prev
    Next
    INDEX
    Explanations

    image-related content or tags

    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
    ipp
    -0.06
    propTypes
    -0.06
    appa
    -0.06
    eer
    -0.06
    hood
    -0.06
     доп
    -0.06
     Minimal
    -0.06
     Schwartz
    -0.06
    anky
    -0.06
    een
    -0.06
    POSITIVE LOGITS
    redients
    0.07
    ëĭĪëĭ¤
    0.07
    tin
    0.07
    autorelease
    0.07
    ires
    0.07
    istrates
    0.07
     thức
    0.06
    redi
    0.06
    OTS
    0.06
    rella
    0.06
    Activations Density 0.002%

    No Known Activations