© 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. 40633
    Prev
    Next
    INDEX
    Explanations

    conjunctions and other connective phrases in complex sentences

    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
    kov
    -0.07
     being
    -0.07
    被
    -0.07
    rowse
    -0.07
     Easily
    -0.06
    _NEED
    -0.06
    uste
    -0.06
     бÑĭÑĤÑĮ
    -0.06
     Mou
    -0.06
     QPoint
    -0.06
    POSITIVE LOGITS
     remove
    0.08
     introduce
    0.07
     add
    0.07
     limit
    0.07
    ikon
    0.07
     removed
    0.07
    htdocs
    0.07
    ÛĮÙĩ
    0.07
     replace
    0.07
     split
    0.07
    Activations Density 0.038%

    No Known Activations