© 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. 39900
    Prev
    Next
    INDEX
    Explanations

    elements related to structured data or code syntax, particularly in programming contexts

    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
    iasi
    -0.07
     Expanded
    -0.06
     Means
    -0.06
     Cl
    -0.06
    Comparer
    -0.06
    ombs
    -0.06
    FLAGS
    -0.06
     Unc
    -0.06
    411
    -0.06
    imest
    -0.05
    POSITIVE LOGITS
    oux
    0.08
    utsche
    0.07
    aru
    0.07
    åĶ¯
    0.07
    .setter
    0.07
    ivec
    0.07
     UIF
    0.06
    WER
    0.06
    elli
    0.06
    ouz
    0.06
    Activations Density 0.006%

    No Known Activations