© 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. 82930
    Prev
    Next
    INDEX
    Explanations

    key terms related to organizations and systems in various contexts

    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
    bris
    -0.06
    aina
    -0.06
    âng
    -0.06
    alah
    -0.06
    uen
    -0.06
    Ø¡
    -0.06
    razier
    -0.06
    ouce
    -0.06
    éis
    -0.06
    aber
    -0.06
    POSITIVE LOGITS
     divided
    0.21
    åĪĨ
    0.18
     split
    0.17
     divide
    0.16
     divides
    0.15
     divid
    0.15
     Divide
    0.14
     Split
    0.13
     three
    0.13
     splits
    0.13
    Activations Density 0.111%

    No Known Activations