© 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 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. 119343
    Prev
    Next
    INDEX
    Explanations

    references to company growth and strategic decisions

    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
     hopefully
    -0.08
    baru
    -0.07
    incinn
    -0.07
     Hopefully
    -0.07
    caff
    -0.07
    Hopefully
    -0.07
     Rosenstein
    -0.07
    æ¡ĥ
    -0.06
     geile
    -0.06
    pid
    -0.06
    POSITIVE LOGITS
     previous
    0.07
    Needs
    0.06
     hadn
    0.06
     avait
    0.06
    pecific
    0.06
     existing
    0.06
    ãģĤãģ£ãģŁ
    0.06
     previously
    0.06
     had
    0.06
    Ñĩил
    0.06
    Activations Density 0.019%

    No Known Activations