© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 76332
    Prev
    Next
    INDEX
    Explanations

    instances of the word "day" in various contexts, particularly with numeric modifiers

    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
    silver
    -0.07
    inate
    -0.06
    -animate
    -0.06
     Russo
    -0.06
    .dataSource
    -0.06
    NSNotification
    -0.06
    slashes
    -0.06
    icut
    -0.06
    iggins
    -0.06
    /fonts
    -0.06
    POSITIVE LOGITS
    dream
    0.08
    son
    0.07
    vault
    0.07
    691
    0.06
    OfWeek
    0.06
    ushima
    0.06
    resher
    0.06
    (day
    0.06
    ss
    0.06
    break
    0.06
    Activations Density 0.018%

    No Known Activations