© 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. 16368
    Prev
    Next
    INDEX
    Explanations

    references to user interactions and comments in online platforms

    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
     Rum
    -0.07
    umpt
    -0.07
    zia
    -0.06
    ancel
    -0.06
    ازÛĮ
    -0.06
     exiting
    -0.06
    ined
    -0.06
    ancer
    -0.06
     Rück
    -0.06
    üss
    -0.06
    POSITIVE LOGITS
     below
    0.09
    below
    0.08
    719
    0.07
    quet
    0.07
    ANJI
    0.07
     abaixo
    0.07
    以ä¸ĭ
    0.07
    idelberg
    0.06
    IFn
    0.06
    irected
    0.06
    Activations Density 0.005%

    No Known Activations