© 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. 73252
    Prev
    Next
    INDEX
    Explanations

    references to separate entities, structures, or systems

    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
     alike
    -0.07
    ÑĥÑĢн
    -0.06
    åIJ¹
    -0.06
    _CHANGED
    -0.06
    eyn
    -0.06
    774
    -0.06
    icho
    -0.06
    ï¼İ
    -0.06
    _EXTENSIONS
    -0.06
    缸
    -0.06
    POSITIVE LOGITS
     separate
    0.21
     Separate
    0.19
     separately
    0.16
     seperate
    0.16
     distinct
    0.12
    çĭ¬ç«ĭ
    0.12
     independent
    0.12
    Separ
    0.12
     separated
    0.11
    Independent
    0.11
    Activations Density 0.030%

    No Known Activations