© 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. 57376
    Prev
    Next
    INDEX
    Explanations

    phrases that convey the theme of revitalization or transformation

    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
    thern
    -0.08
    ÑĪов
    -0.08
    ocker
    -0.07
    izr
    -0.07
    ÃŃnh
    -0.07
    .esp
    -0.07
    ï¼Ĺ
    -0.07
    ÏĢον
    -0.07
    á»ģ
    -0.07
    иÑĢов
    -0.06
    POSITIVE LOGITS
     alive
    0.10
     life
    0.08
    alive
    0.08
     animation
    0.07
    æ´»
    0.07
    çĶŁåij½
    0.07
     live
    0.07
     virtual
    0.07
     full
    0.07
     thus
    0.06
    Activations Density 0.028%

    No Known Activations