© 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. 89098
    Prev
    Next
    INDEX
    Explanations

    phrases that suggest indulgence or enjoyment of food experiences

    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
    оÑī
    -0.07
    jamin
    -0.07
    OLUTE
    -0.07
    essa
    -0.07
    ümÃ¼ÅŁ
    -0.07
    arge
    -0.07
    å®Ļ
    -0.06
    ameron
    -0.06
    ahoma
    -0.06
    azar
    -0.06
    POSITIVE LOGITS
     conventional
    0.09
     usual
    0.08
     traditional
    0.08
    traditional
    0.07
     WALL
    0.07
     ordinary
    0.07
     illicit
    0.06
     Traditional
    0.06
    usual
    0.06
    segue
    0.06
    Activations Density 0.045%

    No Known Activations