© 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. 16906
    Prev
    Next
    INDEX
    Explanations

    instances of significant communication or expressions

    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
    .identity
    -0.06
     Maiden
    -0.06
     cannot
    -0.06
     corporation
    -0.06
     Cheap
    -0.06
     Cov
    -0.06
    Patch
    -0.06
     cheaper
    -0.06
     instead
    -0.06
     Barg
    -0.06
    POSITIVE LOGITS
    æĺŃ
    0.07
    ardo
    0.07
    /lic
    0.07
    çİī
    0.07
    ubl
    0.07
    icensed
    0.06
    âĹİ
    0.06
    Å¡et
    0.06
    ãģĺ
    0.06
    é±
    0.06
    Activations Density 0.000%

    No Known Activations