© 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. 17-LLAMASCOPE-RES-131K
    11. 126952
    Prev
    Next
    INDEX
    Explanations

    references to military aircraft procurement and evaluation

    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
     fractional
    -0.07
    roti
    -0.07
    ILD
    -0.07
     Roose
    -0.07
    ptal
    -0.07
    .scalablytyped
    -0.07
    ittel
    -0.06
    uries
    -0.06
    acci
    -0.06
    _drv
    -0.06
    POSITIVE LOGITS
     purchase
    0.09
    Purchase
    0.08
     purchasing
    0.07
     Purchase
    0.07
     закÑĥп
    0.07
     deal
    0.07
    nos
    0.07
     bilateral
    0.06
     Foreign
    0.06
     purchased
    0.06
    Activations Density 0.019%

    No Known Activations