© 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. 28215
    Prev
    Next
    INDEX
    Explanations

    personal reflections and experiences related to life changes

    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
     Wikipedia
    -0.06
     Kb
    -0.06
    °
    -0.06
    å½¼
    -0.06
     wikipedia
    -0.06
     improvised
    -0.06
    ãĥīãĥ©
    -0.06
     defaultMessage
    -0.06
     unm
    -0.05
    REA
    -0.05
    POSITIVE LOGITS
     blog
    0.10
    blog
    0.09
    .blog
    0.08
     Blog
    0.08
    lez
    0.08
    itore
    0.08
     posts
    0.08
     blogging
    0.08
    .live
    0.07
    apus
    0.07
    Activations Density 0.106%

    No Known Activations