© 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. 73822
    Prev
    Next
    INDEX
    Explanations

    instances of decision-making or actions taken by people or organizations

    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
    Ùħز
    -0.08
    бÑĥдÑĮ
    -0.07
    stagram
    -0.07
    kov
    -0.07
    idl
    -0.07
    \<^
    -0.07
    yz
    -0.07
    à¥įसर
    -0.07
    stay
    -0.07
    mae
    -0.07
    POSITIVE LOGITS
     decided
    0.07
     ed
    0.07
     now
    0.07
     decide
    0.06
     again
    0.06
    ertz
    0.06
    ÅĤ
    0.06
     decision
    0.06
    0.06
     Pope
    0.06
    Activations Density 0.136%

    No Known Activations