© 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. 2172
    Prev
    Next
    INDEX
    Explanations

    instances of the term "evolution" in various contexts

    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
    èĻ
    -0.07
     Gore
    -0.07
    quier
    -0.07
    halb
    -0.07
    ikel
    -0.07
    ãĤ·ãĤ¢
    -0.07
    etch
    -0.06
    owler
    -0.06
     маÑģ
    -0.06
    ORN
    -0.06
    POSITIVE LOGITS
    /release
    0.08
     unserialize
    0.07
     Ward
    0.07
    /connect
    0.07
    Slides
    0.07
    CK
    0.07
    JR
    0.06
     Dok
    0.06
    ogs
    0.06
    /testing
    0.06
    Activations Density 0.053%

    No Known Activations