© 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. 15398
    Prev
    Next
    INDEX
    Explanations

    phrases indicating being enclosed or encircled by various elements

    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
    .scalablytyped
    -0.08
    師
    -0.07
     sperma
    -0.07
    .PerformLayout
    -0.07
    chalk
    -0.07
    ignum
    -0.07
    .synthetic
    -0.07
    oku
    -0.07
     оÑĩеÑĢед
    -0.07
    ecer
    -0.07
    POSITIVE LOGITS
     surrounding
    0.08
    protect
    0.07
     other
    0.06
     around
    0.06
    ack
    0.06
     environment
    0.06
     legend
    0.06
     mountains
    0.06
    ç¨ĭ
    0.06
     surround
    0.06
    Activations Density 0.011%

    No Known Activations