© 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. 86647
    Prev
    Next
    INDEX
    Explanations

    references to organized events or exhibitions

    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
     Leather
    -0.06
     mass
    -0.06
    ilde
    -0.06
     other
    -0.05
     Latter
    -0.05
     bä
    -0.05
    essler
    -0.05
    ardy
    -0.05
    entiful
    -0.05
     spas
    -0.05
    POSITIVE LOGITS
    ADX
    0.08
    èĻŁ
    0.08
    expanded
    0.08
    _increase
    0.07
    agnost
    0.07
    iná
    0.07
    ä»Ĭå¹´
    0.07
    ạc
    0.07
    promise
    0.07
     promises
    0.07
    Activations Density 0.038%

    No Known Activations