© 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. 117748
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and reflections

    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
     Ãĸn
    -0.07
    ĸ
    -0.07
    achel
    -0.07
    |array
    -0.07
    -rock
    -0.06
    _DS
    -0.06
     blowjob
    -0.06
    ãĤĤãĤĬ
    -0.06
    οÏį
    -0.06
     Verd
    -0.06
    POSITIVE LOGITS
     اÙĦرÙħزÙĬØ©
    0.06
     Phong
    0.06
    urg
    0.06
    helm
    0.06
     quite
    0.06
    typ
    0.06
     somewhat
    0.06
     serious
    0.06
    vá
    0.06
    642
    0.06
    Activations Density 0.043%

    No Known Activations