© 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. 89225
    Prev
    Next
    INDEX
    Explanations

    references to methods and comparisons related to measurements and processes

    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
     Dann
    -0.06
     جÙĩت
    -0.06
    emento
    -0.06
    ãn
    -0.06
    ebo
    -0.06
    _transient
    -0.06
     too
    -0.06
     afin
    -0.06
     insufficient
    -0.06
    ाà¤ĸ
    -0.05
    POSITIVE LOGITS
     unlike
    0.10
     fewer
    0.09
     Unlike
    0.09
    Unlike
    0.09
     instead
    0.08
     Instead
    0.07
     Bye
    0.07
    Instead
    0.07
     directly
    0.07
     Pierce
    0.07
    Activations Density 0.028%

    No Known Activations