© 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. 31060
    Prev
    Next
    INDEX
    Explanations

    instances of legal or regulatory processes and decisions

    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
    orb
    -0.06
    km
    -0.06
    alf
    -0.05
    illions
    -0.05
    allen
    -0.05
     chút
    -0.05
     aller
    -0.05
    uddle
    -0.05
     tomorrow
    -0.05
    ko
    -0.05
    POSITIVE LOGITS
    secutive
    0.08
    tings
    0.08
    ocoder
    0.07
    OLA
    0.07
     times
    0.07
    uyla
    0.07
    å±
    0.07
    emap
    0.07
     since
    0.07
    åĪĨåĪ«
    0.07
    Activations Density 0.041%

    No Known Activations