© 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. 119311
    Prev
    Next
    INDEX
    Explanations

    references to canyons and their characteristics

    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
    Sphere
    -0.07
    Ghost
    -0.07
    _extended
    -0.06
    _ghost
    -0.06
    .expires
    -0.06
    жив
    -0.06
    à¹ģà¸ľ
    -0.06
    å»Ĭ
    -0.06
    æ±Ĺ
    -0.06
    vais
    -0.06
    POSITIVE LOGITS
    -bottom
    0.07
    ichi
    0.07
    bottom
    0.07
    alara
    0.07
     sâu
    0.07
     depths
    0.06
    ú
    0.06
     region
    0.06
    ide
    0.06
    -mouth
    0.06
    Activations Density 0.014%

    No Known Activations