© 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. 118668
    Prev
    Next
    INDEX
    Explanations

    expressions related to the effects and qualities of water

    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
     cannot
    -0.07
     compared
    -0.07
    ä¸įè¦ģ
    -0.07
     nowhere
    -0.07
    ä¸įä¼ļ
    -0.06
     shouldn
    -0.06
    ä¸įèĥ½
    -0.06
    алов
    -0.06
     not
    -0.06
    ä¸įæĺ¯
    -0.06
    POSITIVE LOGITS
     instead
    0.20
     Instead
    0.18
    Instead
    0.17
    instead
    0.17
     naopak
    0.12
     Nope
    0.09
     вмеÑģÑĤ
    0.09
     merely
    0.08
     sondern
    0.08
     Nor
    0.08
    Activations Density 0.001%

    No Known Activations