© 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. 128846
    Prev
    Next
    INDEX
    Explanations

    references to technology and its applications

    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
     otherwise
    -0.07
    aka
    -0.07
    ä»Ĭ
    -0.06
     hopefully
    -0.06
     any
    -0.06
     subsequently
    -0.05
    çݰ代
    -0.05
     soon
    -0.05
     or
    -0.05
    Boom
    -0.05
    POSITIVE LOGITS
    çļĦæĺ¯
    0.10
    اÙħÛĮ
    0.09
     quite
    0.08
     tzv
    0.07
     only
    0.07
    ifferent
    0.07
    ноÑģÑıÑĤ
    0.07
    ноÑģи
    0.07
    esian
    0.07
    Ïģκ
    0.07
    Activations Density 0.047%

    No Known Activations