© 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. 80152
    Prev
    Next
    INDEX
    Explanations

    technical terms and jargon related to security and auditing processes

    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
    ici
    -0.07
    ilim
    -0.07
    sein
    -0.06
    Dire
    -0.06
    Wnd
    -0.06
    .Xaml
    -0.06
    antt
    -0.06
    yaw
    -0.06
    /XML
    -0.06
    .registry
    -0.06
    POSITIVE LOGITS
    elden
    0.07
    .fhir
    0.07
    yles
    0.07
    audit
    0.07
     aud
    0.07
    ayo
    0.06
     Aud
    0.06
     Cloud
    0.06
    μαÏĦο
    0.06
    ancial
    0.06
    Activations Density 0.005%

    No Known Activations