© 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. 69468
    Prev
    Next
    INDEX
    Explanations

    elements related to numerical identifiers and formal document structures

    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
     separate
    -0.07
    kas
    -0.06
     âĦĸ
    -0.06
     No
    -0.05
     Interrupt
    -0.05
     Patel
    -0.05
     Hind
    -0.05
    /linux
    -0.05
    ural
    -0.05
     Separate
    -0.05
    POSITIVE LOGITS
    LES
    0.07
    kul
    0.07
    instanc
    0.07
    etas
    0.07
    ckill
    0.07
    hei
    0.07
    acci
    0.07
    tempt
    0.07
    erea
    0.07
    SAFE
    0.07
    Activations Density 0.183%

    No Known Activations