© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 28779
    Prev
    Next
    INDEX
    Explanations

    conjunctions and phrases that indicate relationships or connections between ideas

    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
    olib
    -0.07
    estyle
    -0.07
    orama
    -0.06
    åĨ²
    -0.06
    ij
    -0.06
    ä¸Ńæĸĩ
    -0.06
    -cigarettes
    -0.06
     smo
    -0.06
    999
    -0.06
    923
    -0.06
    POSITIVE LOGITS
     links
    0.08
     analysis
    0.08
     info
    0.08
     information
    0.08
     discussion
    0.07
     pictures
    0.07
     pics
    0.07
     photos
    0.07
    adan
    0.07
    edBy
    0.07
    Activations Density 0.031%

    No Known Activations