© 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. 4950
    Prev
    Next
    INDEX
    Explanations

    phrases related to help and guidance in searching for information

    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
    ISIBLE
    -0.07
    lify
    -0.07
    æµľ
    -0.06
    丸
    -0.06
    ì¹Ļ
    -0.06
    ffen
    -0.06
    bette
    -0.06
    efault
    -0.06
    ijkstra
    -0.06
    §è¡Į
    -0.06
    POSITIVE LOGITS
     needed
    0.08
     needs
    0.07
     sought
    0.07
     elusive
    0.07
     need
    0.07
     cần
    0.06
    -specific
    0.06
     besoin
    0.06
     wanted
    0.06
     desired
    0.06
    Activations Density 0.006%

    No Known Activations