© 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. 9-LLAMASCOPE-RES-131K
    11. 97444
    Prev
    Next
    INDEX
    Explanations

    terms associated with delivery services

    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
    ovit
    -0.07
    avia
    -0.07
    iyi
    -0.07
     reco
    -0.06
    borough
    -0.06
     Athena
    -0.06
    à¸²à¸ł
    -0.06
    каж
    -0.06
     PackageManager
    -0.06
    ured
    -0.06
    POSITIVE LOGITS
    zens
    0.06
    axed
    0.06
    ourse
    0.06
    ìľ¨
    0.06
    759
    0.06
    erse
    0.06
    dda
    0.06
    gren
    0.06
    abel
    0.06
    dens
    0.06
    Activations Density 0.013%

    No Known Activations