Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 5-LLAMASCOPE-RES-131K
    6. 126321
    Prev
    Next
    INDEX
    Explanations

    instances of the word "prepared" and related forms

    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
    olley
    -0.06
    AdminController
    -0.06
     Wade
    -0.06
    olume
    -0.06
    otch
    -0.06
    ropol
    -0.06
    htar
    -0.06
    aurus
    -0.06
    elier
    -0.06
    itto
    -0.06
    POSITIVE LOGITS
    ness
    0.08
     Bid
    0.07
     bid
    0.07
    Bid
    0.07
     prepared
    0.06
     lecturer
    0.06
    prepared
    0.06
     Prepared
    0.06
    ance
    0.06
    234
    0.06
    Activations Density 0.004%

    No Known Activations