© 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. 2280
    Prev
    Next
    INDEX
    Explanations

    references to games and gameplay elements

    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
    å¸Ń
    -0.07
    äºŃ
    -0.07
    меÑĤ
    -0.06
    UFFIX
    -0.06
     silhouette
    -0.06
     Sous
    -0.06
     Tie
    -0.05
    ISMATCH
    -0.05
    ici
    -0.05
     Sunshine
    -0.05
    POSITIVE LOGITS
    legal
    0.07
    arked
    0.07
    à¹Ĥà¸Ĺ
    0.07
    LEGAL
    0.07
     Stable
    0.07
    ahr
    0.06
    olland
    0.06
     lands
    0.06
     RANDOM
    0.06
     intest
    0.06
    Activations Density 0.006%

    No Known Activations