© 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. 14893
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to comprehensive legal and service coverage

    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
    ETA
    -0.06
    Ïĥει
    -0.06
    aal
    -0.06
    ORA
    -0.06
    leon
    -0.06
    ichen
    -0.06
    stem
    -0.06
     zug
    -0.06
     Rash
    -0.06
    FileStream
    -0.05
    POSITIVE LOGITS
     aspects
    0.09
     aspect
    0.08
    aspect
    0.08
     issues
    0.08
     topics
    0.07
     matters
    0.07
    ViewChild
    0.07
     TMPro
    0.07
    issues
    0.06
    topics
    0.06
    Activations Density 0.016%

    No Known Activations