© 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 EvalsExportsinterp-engineNEWAPI 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. 14833
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a strong beginning or kickoff of events

    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
    ông
    -0.08
    mium
    -0.08
    OSE
    -0.07
     WithEvents
    -0.07
    .scalablytyped
    -0.07
    osate
    -0.07
    ÙĪاÙĩ
    -0.07
     ReturnValue
    -0.07
    ãģIJ
    -0.07
    км
    -0.07
    POSITIVE LOGITS
    nings
    0.09
     start
    0.07
    /start
    0.07
    0.07
    start
    0.07
    bars
    0.07
     to
    0.07
    579
    0.06
    ener
    0.06
    989
    0.06
    Activations Density 0.006%

    No Known Activations