© 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. 127450
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "to."

    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
    orem
    -0.07
    ingga
    -0.07
    ing
    -0.07
    yst
    -0.07
     indeed
    -0.06
    (ed
    -0.06
    hai
    -0.06
    ury
    -0.06
    AYS
    -0.06
     Exactly
    -0.06
    POSITIVE LOGITS
     other
    0.10
    'autres
    0.09
     what
    0.08
    ouses
    0.08
    other
    0.08
     others
    0.08
     ones
    0.07
    åħ¶ä»ĸ
    0.07
     those
    0.07
     usual
    0.07
    Activations Density 0.018%

    No Known Activations