© 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. 80326
    Prev
    Next
    INDEX
    Explanations

    programming constructs and identifiers related to data structures and operations

    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
    ylon
    -0.08
    avra
    -0.08
    -await
    -0.07
     Sist
    -0.07
    achuset
    -0.07
    umbn
    -0.07
    yscale
    -0.07
     اÙĨر
    -0.07
    cheid
    -0.07
    zzle
    -0.07
    POSITIVE LOGITS
    upp
    0.07
     mo
    0.06
     Barth
    0.06
     pur
    0.06
    others
    0.06
    kas
    0.06
     Economist
    0.06
    osp
    0.06
     others
    0.06
    ote
    0.05
    Activations Density 0.052%

    No Known Activations