© 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. 17-LLAMASCOPE-RES-131K
    11. 83853
    Prev
    Next
    INDEX
    Explanations

    concepts related to optimization and planning strategies

    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
    pitch
    -0.09
     bid
    -0.07
    uchar
    -0.07
    Pitch
    -0.07
     cong
    -0.07
    igner
    -0.07
    omik
    -0.07
    eday
    -0.06
     pitch
    -0.06
    Bid
    -0.06
    POSITIVE LOGITS
    481
    0.06
     onCancelled
    0.06
    ourg
    0.06
    isser
    0.06
    ité
    0.05
    oad
    0.05
    سÙĪب
    0.05
     Subcommittee
    0.05
    .updateDynamic
    0.05
    ุà¸ķ
    0.05
    Activations Density 0.008%

    No Known Activations