© 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. 17-LLAMASCOPE-RES-131K
    11. 16957
    Prev
    Next
    INDEX
    Explanations

    concerns and discussions surrounding the risks of artificial intelligence

    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
    važ
    -0.07
    urgeon
    -0.07
    .getOwnProperty
    -0.07
    ervo
    -0.07
     helicopt
    -0.07
    KO
    -0.07
    olv
    -0.06
    erp
    -0.06
    urf
    -0.06
     ilet
    -0.06
    POSITIVE LOGITS
     Freed
    0.07
     AI
    0.07
     super
    0.07
     scenario
    0.06
     runaway
    0.06
     Bios
    0.06
     fro
    0.06
     scenarios
    0.06
     bios
    0.06
     Scenario
    0.05
    Activations Density 0.008%

    No Known Activations