© 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. 17517
    Prev
    Next
    INDEX
    Explanations

    references to flights and related logistical details

    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
    ervo
    -0.09
    ÑĮко
    -0.07
    ยà¸ĩ
    -0.07
    åijĬ
    -0.07
    iske
    -0.07
     prostitut
    -0.07
    inq
    -0.06
    (=)
    -0.06
    endants
    -0.06
    uetype
    -0.06
    POSITIVE LOGITS
     ranks
    0.07
     hell
    0.07
    odu
    0.07
     process
    0.07
    hell
    0.06
     motions
    0.06
     stages
    0.06
     sieve
    0.06
     processo
    0.06
     channels
    0.06
    Activations Density 0.080%

    No Known Activations