© 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. 124726
    Prev
    Next
    INDEX
    Explanations

    elements related to food names and descriptions

    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
    ëį°ìĿ´íĬ¸
    -0.10
    ,eg
    -0.09
    .MixedReality
    -0.08
    OffsetTable
    -0.08
     pestic
    -0.08
     ฿
    -0.08
     Ekon
    -0.08
    serter
    -0.08
    iyon
    -0.08
     *(*
    -0.08
    POSITIVE LOGITS
     (
    0.06
    Question
    0.05
     "
    0.05
    Âł
    0.05
    mic
    0.05
     ?
    0.05
     gist
    0.05
    É
    0.05
    0.05
     Guest
    0.05
    Activations Density 0.609%

    No Known Activations