© 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. 88427
    Prev
    Next
    INDEX
    Explanations

    technical specifications and advancements in network architecture

    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
    adel
    -0.07
    hev
    -0.06
    irts
    -0.06
     bureau
    -0.06
    å¸ĥ
    -0.06
     sple
    -0.06
    unter
    -0.06
     pie
    -0.06
    æ½®
    -0.06
    uzzy
    -0.06
    POSITIVE LOGITS
    InputLabel
    0.07
    ImageContext
    0.07
    attention
    0.07
    ông
    0.07
    .MSG
    0.07
    (global
    0.07
    ibel
    0.07
     attends
    0.06
    mask
    0.06
    Attention
    0.06
    Activations Density 0.080%

    No Known Activations