© 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. 15-LLAMASCOPE-RES-131K
    11. 104249
    Prev
    Next
    INDEX
    Explanations

    references to inspections and evaluations related to facilities or farms

    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
    пÑĢиклад
    -0.07
    æĮ¯
    -0.07
    ëĮ
    -0.07
    .toCharArray
    -0.07
     naï
    -0.06
    hangi
    -0.06
     Champ
    -0.06
    .scalajs
    -0.06
     scand
    -0.06
    ekl
    -0.06
    POSITIVE LOGITS
     identified
    0.07
    unes
    0.07
    ipse
    0.07
     Identified
    0.06
    arcy
    0.06
    -touch
    0.06
    æ¶ī
    0.06
    -inline
    0.06
     already
    0.06
    axon
    0.06
    Activations Density 0.014%

    No Known Activations