© 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. 86738
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the introduction of new methods or representations in research

    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
    stroy
    -0.06
    occ
    -0.06
    .lo
    -0.06
    oster
    -0.06
    eland
    -0.06
    maf
    -0.06
     Tir
    -0.06
    metic
    -0.06
     mand
    -0.06
    Specification
    -0.05
    POSITIVE LOGITS
     approach
    0.12
     method
    0.10
     framework
    0.09
    æĸ¹æ³ķ
    0.08
     Approach
    0.08
    ä¸Ģç§į
    0.08
     technique
    0.08
    method
    0.07
    appro
    0.07
    iola
    0.07
    Activations Density 0.063%

    No Known Activations