© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 90814
    Prev
    Next
    INDEX
    Explanations

    phrases indicating anticipation or future actions

    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
    abyrin
    -0.07
    åĺĽ
    -0.07
    &m
    -0.06
    ternet
    -0.06
    quat
    -0.06
    å¾Ĵ
    -0.06
     Cron
    -0.06
    bia
    -0.06
     Spirits
    -0.06
    кеÑĤ
    -0.06
    POSITIVE LOGITS
    eza
    0.07
     future
    0.07
     Thirty
    0.06
    jac
    0.06
    cesso
    0.06
    ابر
    0.06
    igor
    0.06
     Blanc
    0.06
     Bra
    0.06
     Peak
    0.06
    Activations Density 0.001%

    No Known Activations