© 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. 84106
    Prev
    Next
    INDEX
    Explanations

    references to work schedules and shift patterns

    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
    BYTE
    -0.07
    rita
    -0.07
     Sesso
    -0.07
    tracks
    -0.07
    .openConnection
    -0.07
    urat
    -0.07
    ãĥ³ãĥķ
    -0.07
    ettel
    -0.07
    ideo
    -0.07
    èĦ
    -0.07
    POSITIVE LOGITS
     shifts
    0.09
     duty
    0.09
     shift
    0.09
    shift
    0.09
     duties
    0.09
     rotating
    0.08
    rot
    0.07
     Shift
    0.07
     rotation
    0.07
    Shift
    0.07
    Activations Density 0.037%

    No Known Activations