© 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. 56146
    Prev
    Next
    INDEX
    Explanations

    references to nature and outdoor environments

    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
    isel
    -0.08
    WND
    -0.07
    ëĬ¥
    -0.07
    emann
    -0.07
    zin
    -0.07
    essler
    -0.07
    ÏĦÏħ
    -0.07
    Ðĭ
    -0.06
    chai
    -0.06
    ãģĤãĤĬ
    -0.06
    POSITIVE LOGITS
     while
    0.09
     or
    0.09
     yourself
    0.08
     whilst
    0.08
    while
    0.08
     either
    0.08
     Alternatively
    0.07
     mentre
    0.07
     While
    0.07
    ï¼ĮæĪĸ
    0.07
    Activations Density 0.030%

    No Known Activations