© 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. 108218
    Prev
    Next
    INDEX
    Explanations

    variations of the phrase "can be" along with their context

    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
    /MPL
    -0.07
    .scalablytyped
    -0.07
     extr
    -0.07
    .EventQueue
    -0.07
    _marshall
    -0.07
    871
    -0.07
    amik
    -0.07
    Automatic
    -0.07
    352
    -0.07
    848
    -0.06
    POSITIVE LOGITS
    peater
    0.06
    å¾
    0.06
    ãģķãĤī
    0.06
     boon
    0.06
     backs
    0.06
    sten
    0.06
     Choose
    0.06
    Choose
    0.06
     interchange
    0.06
    ivers
    0.06
    Activations Density 0.012%

    No Known Activations