Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43400
    Prev
    Next
    INDEX
    Explanations

    phrases related to planning or making preparations in advance

    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
    reh
    -0.09
    ettes
    -0.07
     avanz
    -0.07
     advancing
    -0.07
     advances
    -0.07
     advancements
    -0.07
    adv
    -0.07
    rette
    -0.07
    late
    -0.07
    _adv
    -0.07
    POSITIVE LOGITS
     planning
    0.10
     of
    0.09
     notice
    0.09
    /on
    0.08
     scheduling
    0.08
     booking
    0.08
     via
    0.08
     time
    0.08
     preparation
    0.08
     Planning
    0.08
    Activations Density 0.014%

    No Known Activations