© 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. 127084
    Prev
    Next
    INDEX
    Explanations

    concepts related to the essence and characteristics of nature

    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
    raud
    -0.09
    lech
    -0.08
    ongyang
    -0.08
    aison
    -0.08
    alleries
    -0.07
    æ¶ī
    -0.07
    obraz
    -0.07
    actionDate
    -0.07
    ÙĪÙģ
    -0.07
    们
    -0.07
    POSITIVE LOGITS
    ness
    0.07
     nature
    0.06
    ality
    0.06
     Rt
    0.06
    liness
    0.06
     Farr
    0.06
    adas
    0.06
    lessness
    0.06
     ethic
    0.06
     tone
    0.05
    Activations Density 0.046%

    No Known Activations