© 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 EvalsExportsinterp-engineNEWAPI 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. 14759
    Prev
    Next
    INDEX
    Explanations

    references to significant events or highlights in a specific time period

    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
    ">ÃĹ</
    -0.07
     Takım
    -0.06
    ronics
    -0.06
    orsk
    -0.06
     formally
    -0.06
    arrant
    -0.06
    efs
    -0.06
     ImageIcon
    -0.06
     âĢ¦↵↵
    -0.06
     fon
    -0.06
    POSITIVE LOGITS
    Exceptions
    0.07
    Incoming
    0.07
     crop
    0.06
    ubat
    0.06
    argar
    0.06
     slate
    0.06
     Ú©ÛĮÙģ
    0.06
    ino
    0.06
    afil
    0.06
    TECTED
    0.06
    Activations Density 0.024%

    No Known Activations