© 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. 84882
    Prev
    Next
    INDEX
    Explanations

    references to profit and profitability in various contexts

    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
    eri
    -0.08
    er
    -0.07
    ź
    -0.07
    riot
    -0.06
    erk
    -0.06
    ported
    -0.06
    -thirds
    -0.06
    oral
    -0.06
    icast
    -0.06
    881
    -0.06
    POSITIVE LOGITS
    ably
    0.12
    ession
    0.08
    äre
    0.08
    ocols
    0.08
    çİĩ
    0.08
    loss
    0.08
    shire
    0.07
    SCAN
    0.07
    ären
    0.07
     nhuáºŃn
    0.07
    Activations Density 0.008%

    No Known Activations