© 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. 92884
    Prev
    Next
    INDEX
    Explanations

    segments of code or technical references

    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
    .scalablytyped
    -0.08
    大åħ¨
    -0.08
    rive
    -0.07
    eÄį
    -0.07
    пиÑģ
    -0.07
     кÑĢок
    -0.07
    udur
    -0.07
    Ģ
    -0.07
     addCriterion
    -0.07
    .Debugger
    -0.07
    POSITIVE LOGITS
     break
    0.08
     return
    0.07
    ENTE
    0.06
    _pb
    0.06
     Stan
    0.06
    ¼
    0.06
     continue
    0.06
     cres
    0.06
     pass
    0.06
     dr
    0.05
    Activations Density 0.092%

    No Known Activations