© 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 EvalsExportsAPI 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. 71278
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or equations related to physical phenomena

    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
    chet
    -0.08
    âĢ¦↵↵↵
    -0.08
    å²
    -0.07
    asar
    -0.07
    keley
    -0.07
    theon
    -0.07
    iali
    -0.07
    _tE
    -0.07
    isz
    -0.07
    eyJ
    -0.07
    POSITIVE LOGITS
     Pods
    0.07
     pods
    0.06
     Revel
    0.06
    @brief
    0.05
     SUS
    0.05
     patron
    0.05
    380
    0.05
     mans
    0.05
     dro
    0.05
    ween
    0.05
    Activations Density 0.576%

    No Known Activations