© 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. 56602
    Prev
    Next
    INDEX
    Explanations

    instances of the word "to" used in various contexts and associated phrases

    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
    еви
    -0.07
    linger
    -0.06
    ¼
    -0.06
    zan
    -0.06
    ais
    -0.06
    å®Įæķ´
    -0.06
    ζÏĮ
    -0.06
     vidé
    -0.06
    зÑĥ
    -0.06
    ÑĮÑİÑĤ
    -0.06
    POSITIVE LOGITS
     only
    0.12
    only
    0.09
    åıªæľī
    0.09
     ONLY
    0.08
     apenas
    0.08
     just
    0.08
     лиÑĪÑĮ
    0.08
     Only
    0.08
     confines
    0.08
     hanya
    0.07
    Activations Density 0.016%

    No Known Activations