© 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. 59012
    Prev
    Next
    INDEX
    Explanations

    specific numeric values associated with protein-related data

    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
    //{{
    -0.08
    adden
    -0.07
    .until
    -0.06
    esian
    -0.06
    UND
    -0.06
    .scalablytyped
    -0.06
    wrapper
    -0.06
    çŃĭ
    -0.06
    subpackage
    -0.06
    æł¼
    -0.06
    POSITIVE LOGITS
    -toggler
    0.07
    ialis
    0.07
    etler
    0.06
    otel
    0.06
    .ali
    0.06
    okane
    0.06
    ZA
    0.06
     Annunci
    0.06
    gan
    0.06
    omm
    0.06
    Activations Density 0.071%

    No Known Activations