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

    Neuronpedia

    Jacobian LensNEW
    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. 85649
    Prev
    Next
    INDEX
    Explanations

    instances of the word "to" and its various uses in the context of actions or intentions

    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
    ikh
    -0.07
    argas
    -0.07
    556
    -0.07
    strain
    -0.07
    dda
    -0.07
    edic
    -0.06
    èĶµ
    -0.06
    adece
    -0.06
    elper
    -0.06
    cade
    -0.06
    POSITIVE LOGITS
    uet
    0.07
    ocument
    0.06
    gere
    0.06
    opo
    0.06
    .postMessage
    0.06
    bara
    0.06
     [](
    0.06
    iju
    0.06
    virt
    0.06
    heck
    0.06
    Activations Density 0.012%

    No Known Activations