© 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. 9-LLAMASCOPE-RES-131K
    11. 94987
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references to court rulings

    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
     FileInfo
    -0.07
    elle
    -0.07
    alk
    -0.06
    Decode
    -0.06
    lot
    -0.06
    issen
    -0.06
    lie
    -0.06
    ayacak
    -0.06
     DefaultValue
    -0.06
     Habit
    -0.06
    POSITIVE LOGITS
    iž
    0.08
    .MixedReality
    0.07
    Å¡t
    0.07
    ,[],
    0.07
     pon
    0.07
    .dex
    0.07
    rama
    0.06
    MOTE
    0.06
    poi
    0.06
    olio
    0.06
    Activations Density 0.012%

    No Known Activations