© 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. 70841
    Prev
    Next
    INDEX
    Explanations

    copyright-related terminology and attributions

    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
    ifer
    -0.07
    asi
    -0.07
    356
    -0.07
    наÑĤ
    -0.06
    oldem
    -0.06
    essor
    -0.06
    reste
    -0.06
     ib
    -0.06
     McN
    -0.06
    оÑĩно
    -0.06
    POSITIVE LOGITS
    avel
    0.07
    ROWSER
    0.06
     éĹ
    0.06
    озем
    0.06
    rone
    0.06
    нÑĮ
    0.06
    OST
    0.06
    sel
    0.06
    便
    0.06
    ned
    0.06
    Activations Density 0.001%

    No Known Activations