© 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. 91981
    Prev
    Next
    INDEX
    Explanations

    descriptions of experiences related to food and enjoyment

    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
    olon
    -0.07
     éĸ
    -0.07
    rrha
    -0.07
    arto
    -0.07
    LOS
    -0.07
    ataka
    -0.07
    TRACE
    -0.07
     commission
    -0.06
    sdale
    -0.06
    borg
    -0.06
    POSITIVE LOGITS
     checkpoint
    0.06
    .Dictionary
    0.06
     Nep
    0.06
     ourselves
    0.06
    åĶ¯
    0.06
     fitte
    0.06
    -transitional
    0.06
     nues
    0.06
     rumored
    0.05
    ERSHEY
    0.05
    Activations Density 0.001%

    No Known Activations