© 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. 72667
    Prev
    Next
    INDEX
    Explanations

    references to the behavior and management of sheep

    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
    ograd
    -0.06
     dial
    -0.06
    æ»
    -0.06
    uzzer
    -0.06
     Cater
    -0.06
     cravings
    -0.06
    RIA
    -0.06
    332
    -0.06
    \Migrations
    -0.06
    uche
    -0.06
    POSITIVE LOGITS
     stamp
    0.07
    اÙĦÙĩ
    0.06
    ì¶ľ
    0.06
    жи
    0.06
    ÑĢÑĥÑĩ
    0.06
    uman
    0.06
    istrar
    0.06
    edException
    0.06
    antics
    0.06
    ót
    0.06
    Activations Density 0.010%

    No Known Activations