© 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 EvalsExportsinterp-engineNEWAPI 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. 69863
    Prev
    Next
    INDEX
    Explanations

    technical terms and processes related to cryptography and security algorithms

    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
    und
    -0.06
     closed
    -0.06
    olson
    -0.06
    tach
    -0.06
    ab
    -0.06
    ADR
    -0.06
    adian
    -0.06
    735
    -0.06
    iphers
    -0.06
    æĬĺ
    -0.06
    POSITIVE LOGITS
     Commit
    0.07
     reve
    0.07
    usercontent
    0.07
    richt
    0.06
    rossover
    0.06
    orias
    0.06
     Sanct
    0.06
     commitments
    0.06
     secrets
    0.06
     oracle
    0.06
    Activations Density 0.032%

    No Known Activations