© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 29813
    Prev
    Next
    INDEX
    Explanations

    references to different types of habitats and geographical features

    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
     woodland
    -0.07
     southwest
    -0.06
    åĿª
    -0.06
     Luft
    -0.06
    ema
    -0.06
    аков
    -0.06
     stanov
    -0.06
     helicopt
    -0.06
     VERBOSE
    -0.06
    afil
    -0.06
    POSITIVE LOGITS
    ollipop
    0.07
     mountains
    0.07
     interfaces
    0.07
     connector
    0.06
    iji
    0.06
     fields
    0.06
     river
    0.06
     areas
    0.06
     flat
    0.06
    òa
    0.06
    Activations Density 0.037%

    No Known Activations