© 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. 15-LLAMASCOPE-RES-131K
    11. 472
    Prev
    Next
    INDEX
    Explanations

    terms related to safety and waste management in the context of radioactive materials

    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
    ngr
    -0.08
    ocode
    -0.07
    tere
    -0.07
    uzzi
    -0.07
    _IRQ
    -0.07
    qa
    -0.07
    ansi
    -0.07
    nev
    -0.07
    endet
    -0.07
    orry
    -0.07
    POSITIVE LOGITS
     eventual
    0.06
    _extent
    0.06
    ãĤ¤ãĥī
    0.06
    arkan
    0.05
    burger
    0.05
     tempo
    0.05
     Lad
    0.05
     tut
    0.05
    à¤ķरण
    0.05
     dumped
    0.05
    Activations Density 0.004%

    No Known Activations