© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 5-LLAMASCOPE-RES-131K
    11. 126666
    Prev
    Next
    INDEX
    Explanations

    terms related to natural processes and phenomena

    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
    emi
    -0.06
    inous
    -0.06
    _rx
    -0.06
    onna
    -0.06
    ³
    -0.05
     Screw
    -0.05
    ep
    -0.05
    ()(
    -0.05
     днÑı
    -0.05
    phon
    -0.05
    POSITIVE LOGITS
    usan
    0.07
    Gift
    0.07
     natural
    0.07
    istically
    0.07
    太éĥİ
    0.07
    θÏħ
    0.07
    ÑĥÑĤи
    0.07
    ĴĮ
    0.07
     gift
    0.07
    Frameworks
    0.07
    Activations Density 0.010%

    No Known Activations