© 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. 17-LLAMASCOPE-RES-131K
    11. 93791
    Prev
    Next
    INDEX
    Explanations

    financial transactions and travel arrangements related to restaurants and airports

    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
    iky
    -0.08
    .pb
    -0.07
    ersh
    -0.07
    iddi
    -0.07
    ebi
    -0.07
    ARGER
    -0.07
    umont
    -0.07
     prostitut
    -0.07
     addCriterion
    -0.07
    rote
    -0.07
    POSITIVE LOGITS
     ,
    0.08
     Wit
    0.07
    0.06
     Vive
    0.06
     Neutral
    0.06
     Bod
    0.05
     .
    0.05
    ibold
    0.05
     Mari
    0.05
    asz
    0.05
    Activations Density 0.016%

    No Known Activations