© 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. 15-LLAMASCOPE-RES-131K
    11. 583
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to data serialization and programming concepts

    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
    ailles
    -0.06
     Soph
    -0.06
     Bread
    -0.06
     bottom
    -0.05
     inputs
    -0.05
    jal
    -0.05
    åĪº
    -0.05
     tiles
    -0.05
    sg
    -0.05
    ttp
    -0.05
    POSITIVE LOGITS
    .writeObject
    0.09
     ObjectOutputStream
    0.08
    aterno
    0.08
    iez
    0.08
    odem
    0.07
     mxArray
    0.07
     INLINE
    0.07
     ÑĤепло
    0.07
    اÙĬت
    0.07
    inaire
    0.07
    Activations Density 0.023%

    No Known Activations