© 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. 16257
    Prev
    Next
    INDEX
    Explanations

    terms related to contract renewals and financial agreements

    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
    aney
    -0.06
    871
    -0.06
    aben
    -0.06
    ninger
    -0.06
    ville
    -0.06
    linger
    -0.06
     hedge
    -0.05
     Gür
    -0.05
    acb
    -0.05
     universal
    -0.05
    POSITIVE LOGITS
     extension
    0.10
    extend
    0.09
     extensions
    0.09
     extend
    0.09
     Extend
    0.09
    /extensions
    0.09
    -extension
    0.08
    Extend
    0.08
     Extension
    0.08
    blink
    0.08
    Activations Density 0.007%

    No Known Activations