© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 76738
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "do" and its various forms in the context of taking action or performing tasks

    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
    ont
    -0.07
    adena
    -0.06
    ulum
    -0.06
    inned
    -0.06
    awl
    -0.06
    egin
    -0.06
    aina
    -0.06
     soll
    -0.06
    %%%%%%%%%%%%%%%%
    -0.06
    ellung
    -0.06
    POSITIVE LOGITS
    toolbox
    0.07
     unreachable
    0.07
    erd
    0.07
    ÙIJÙħ
    0.06
    regor
    0.06
    InBackground
    0.06
    zhou
    0.06
    tings
    0.06
    ãĤ
    0.06
    Impossible
    0.06
    Activations Density 0.021%

    No Known Activations