© 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. 123810
    Prev
    Next
    INDEX
    Explanations

    the repeated use of the phrase "waiting for."

    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
     VÅ¡ech
    -0.09
    _escape
    -0.07
    essions
    -0.07
    _HW
    -0.07
    -chart
    -0.06
     заÑģÑĤав
    -0.06
    cestor
    -0.06
    orgt
    -0.06
    anden
    -0.06
    mise
    -0.06
    POSITIVE LOGITS
     opportunity
    0.08
     to
    0.07
     Opportunity
    0.07
     someone
    0.07
     opportunities
    0.06
    æľī人
    0.06
     results
    0.06
     opport
    0.06
    Moder
    0.06
     contrary
    0.06
    Activations Density 0.010%

    No Known Activations