© 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. 106715
    Prev
    Next
    INDEX
    Explanations

    descriptive attributes and flavors related to food and drink

    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
    oleans
    -0.08
     smell
    -0.08
    podob
    -0.07
    SetColor
    -0.06
     smells
    -0.06
    stdafx
    -0.06
    chema
    -0.06
    ãĥ¬ãĥĵ
    -0.06
    _macros
    -0.06
    oma
    -0.06
    POSITIVE LOGITS
     finish
    0.08
     swallow
    0.07
    finish
    0.07
     Finish
    0.07
     finishing
    0.06
    elper
    0.06
    anson
    0.06
    onen
    0.06
     landscape
    0.06
    _WM
    0.06
    Activations Density 0.007%

    No Known Activations