© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 88220
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to guarantees and assurances of quality or service

    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
    ken
    -0.07
    /games
    -0.07
    adas
    -0.07
    ichel
    -0.07
    ho
    -0.07
     nack
    -0.07
    kest
    -0.07
    ova
    -0.07
     kond
    -0.07
    .isNull
    -0.07
    POSITIVE LOGITS
     guaranteed
    0.09
     Guaranteed
    0.08
     guarantees
    0.07
    anteed
    0.06
    ergus
    0.06
     guarantee
    0.06
    omu
    0.06
    rab
    0.06
     minimal
    0.06
    GU
    0.06
    Activations Density 0.039%

    No Known Activations