© 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. 120688
    Prev
    Next
    INDEX
    Explanations

    keywords related to booking and payment policies

    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
    PRINTF
    -0.07
    777
    -0.06
    quip
    -0.06
    ìĸ¼
    -0.06
     Fetch
    -0.06
     reporting
    -0.06
    æĪ¸
    -0.06
    382
    -0.06
    816
    -0.06
     Utf
    -0.06
    POSITIVE LOGITS
    Locator
    0.07
    .dp
    0.07
    دار
    0.06
    竹
    0.06
    .sax
    0.06
    acky
    0.06
    ager
    0.06
    ÑĮÑĤе
    0.06
    ÙĪاÙĨ
    0.06
    arty
    0.06
    Activations Density 0.006%

    No Known Activations