© 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. 82852
    Prev
    Next
    INDEX
    Explanations

    terms related to cryptographic processes and key management

    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
    ustum
    -0.07
    pillar
    -0.07
    agy
    -0.06
    hed
    -0.06
    ylan
    -0.06
    PEAT
    -0.06
    peater
    -0.06
    nc
    -0.06
    pit
    -0.06
    akit
    -0.06
    POSITIVE LOGITS
     Alice
    0.07
     unique
    0.07
    onta
    0.06
     associated
    0.06
     UNIQUE
    0.06
    ovsky
    0.06
    .sk
    0.06
     signature
    0.06
    setLayout
    0.06
    Å¡ov
    0.06
    Activations Density 0.007%

    No Known Activations