© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 80832
    Prev
    Next
    INDEX
    Explanations

    references to uncertainty about the future and the process of waiting for outcomes

    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
    bourg
    -0.07
    ç¶
    -0.07
    keh
    -0.07
     suche
    -0.07
    Ķ
    -0.07
    ylland
    -0.06
    otor
    -0.06
     DeepCopy
    -0.06
    ede
    -0.06
    æĶ¿
    -0.06
    POSITIVE LOGITS
     future
    0.08
     tomorrow
    0.07
     opportunities
    0.07
    future
    0.07
    .Instance
    0.07
     opportunity
    0.07
    asty
    0.07
     Outcome
    0.07
     outcome
    0.07
    aven
    0.07
    Activations Density 0.030%

    No Known Activations