© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4049
    Prev
    Next
    INDEX
    Explanations

    mentions of biological processes and physical interactions

    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
    ailable
    -0.08
    dez
    -0.07
    ãģ£ãģ¡
    -0.07
    ilot
    -0.07
    èĻķ
    -0.07
    habi
    -0.07
    ugins
    -0.07
     recipients
    -0.06
    idis
    -0.06
    ieres
    -0.06
    POSITIVE LOGITS
     arrival
    0.15
     visit
    0.15
     visiting
    0.15
     arrive
    0.14
     arrives
    0.14
     arrivals
    0.14
     arriving
    0.13
     arrived
    0.13
     visite
    0.13
     coming
    0.13
    Activations Density 0.005%

    No Known Activations