© 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. 61481
    Prev
    Next
    INDEX
    Explanations

    company names and employment-related terms

    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
    apter
    -0.08
    ilden
    -0.07
     quartz
    -0.06
    ellite
    -0.06
    ombo
    -0.06
    resses
    -0.06
    patches
    -0.06
    ovny
    -0.06
    ulu
    -0.06
     primaries
    -0.06
    POSITIVE LOGITS
     summer
    0.12
    summer
    0.11
     Summer
    0.10
    Summer
    0.10
     å¤ı
    0.08
    å¤ı
    0.08
    ummer
    0.07
     intern
    0.07
     internship
    0.07
    summ
    0.07
    Activations Density 0.347%

    No Known Activations