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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 4933
    Prev
    Next
    INDEX
    Explanations

    references to business turnover and VAT registration

    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
    ίδ
    -0.06
    iker
    -0.06
     CALLBACK
    -0.06
    evi
    -0.06
    áct
    -0.06
     deferred
    -0.06
    ÙĥÙĬÙĬÙģ
    -0.06
    Ïģαβ
    -0.06
    resa
    -0.06
     ÎijÏģÏĩ
    -0.06
    POSITIVE LOGITS
     threshold
    0.07
     Revenue
    0.07
    UCH
    0.07
     thresholds
    0.07
    ey
    0.06
     EITHER
    0.06
    threshold
    0.06
    iah
    0.06
    Criterion
    0.06
    Revenue
    0.06
    Activations Density 0.015%

    No Known Activations