© 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. 30485
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to governmental reports and educational contexts

    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
    roy
    -0.06
     dred
    -0.06
     hist
    -0.06
     Fior
    -0.06
    ROY
    -0.06
     wear
    -0.05
     воÑģ
    -0.05
     stretch
    -0.05
     Wear
    -0.05
    nex
    -0.05
    POSITIVE LOGITS
    uilder
    0.08
    .Rad
    0.08
     Cancer
    0.08
     rad
    0.07
     cancer
    0.07
    SourceType
    0.07
    lung
    0.07
     uranium
    0.07
     Radiation
    0.07
    anean
    0.07
    Activations Density 0.001%

    No Known Activations