© 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. 61933
    Prev
    Next
    INDEX
    Explanations

    references to AWS core functionalities and configurations

    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
    ÎĶ
    -0.06
    inda
    -0.06
    stoff
    -0.06
    rix
    -0.06
    anne
    -0.06
    eteor
    -0.05
    icle
    -0.05
    deo
    -0.05
     isot
    -0.05
    shit
    -0.05
    POSITIVE LOGITS
    ìĤ¬ì§Ģ
    0.08
    .kernel
    0.08
    âĦĸâĦĸ
    0.07
    ãģĺ
    0.07
    ез
    0.07
    llib
    0.07
    ãģ£
    0.07
    hack
    0.07
    ARRANT
    0.07
    UDENT
    0.07
    Activations Density 0.001%

    No Known Activations