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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 61667
    Prev
    Next
    INDEX
    Explanations

    references to purchasing and supply-related activities

    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
    ãĥ³ãĥī
    -0.07
     shell
    -0.06
    adro
    -0.06
    fe
    -0.06
    vertis
    -0.06
    ApplicationBuilder
    -0.06
    .slim
    -0.06
    .slot
    -0.06
     паÑģ
    -0.06
    ENDOR
    -0.06
    POSITIVE LOGITS
     supplies
    0.11
     supply
    0.09
     kits
    0.08
     Supplies
    0.08
     needed
    0.07
     Moderator
    0.07
    -needed
    0.07
    èĢĹ
    0.07
     necessary
    0.07
    Supply
    0.07
    Activations Density 0.162%

    No Known Activations