© 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. 15-LLAMASCOPE-RES-131K
    11. 88288
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the introduction or launch of new products or initiatives

    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
    eler
    -0.07
     otherwise
    -0.07
    eth
    -0.07
     Otherwise
    -0.06
    auc
    -0.06
    олÑĸ
    -0.06
    h
    -0.05
    ophy
    -0.05
    atis
    -0.05
    á»iji
    -0.05
    POSITIVE LOGITS
     another
    0.11
    another
    0.10
    åı¦ä¸Ģ
    0.10
     similar
    0.09
     equally
    0.09
     similarly
    0.09
     version
    0.09
     second
    0.08
     nữa
    0.08
     versions
    0.08
    Activations Density 0.029%

    No Known Activations