© 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. 15727
    Prev
    Next
    INDEX
    Explanations

    instances of the word "to" used in various contexts, emphasizing purpose or intent

    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
    verter
    -0.07
     |
    -0.07
    allest
    -0.06
    olas
    -0.06
    opoulos
    -0.06
    riel
    -0.06
    rias
    -0.06
     Hath
    -0.06
    nt
    -0.05
    verture
    -0.05
    POSITIVE LOGITS
    ipc
    0.08
    istrovstvÃŃ
    0.07
    ÑĢек
    0.07
    fec
    0.07
    irket
    0.07
    IPC
    0.07
    kke
    0.06
    hog
    0.06
    oux
    0.06
    aed
    0.06
    Activations Density 0.019%

    No Known Activations