© 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. 129779
    Prev
    Next
    INDEX
    Explanations

    phrases related to home design and decoration

    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
     záv
    -0.07
    raction
    -0.07
    .scalablytyped
    -0.06
    shm
    -0.06
    rish
    -0.06
    entai
    -0.06
    ugu
    -0.06
    ibo
    -0.06
    Ñĥг
    -0.06
     詳細
    -0.06
    POSITIVE LOGITS
    dos
    0.07
     DISCLAIMER
    0.06
    955
    0.06
    _chip
    0.06
    argo
    0.06
    å±ħ
    0.06
    Bat
    0.06
    bat
    0.06
    ÑĢÑĥÑĤ
    0.06
    Throws
    0.06
    Activations Density 0.002%

    No Known Activations