© 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. 89235
    Prev
    Next
    INDEX
    Explanations

    terms related to things or concepts being outdated or obsolete

    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
     latest
    -0.06
    856
    -0.06
    (s
    -0.06
    -0.06
    ajor
    -0.06
     recent
    -0.06
     Kong
    -0.05
    947
    -0.05
    ↵
    -0.05
    848
    -0.05
    POSITIVE LOGITS
    /new
    0.11
    -fashioned
    0.10
    unami
    0.09
    -looking
    0.08
    hipster
    0.08
    -old
    0.08
    à¹īà¸ĩ
    0.08
    æİī
    0.08
    usan
    0.08
    esser
    0.08
    Activations Density 0.008%

    No Known Activations