© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 74435
    Prev
    Next
    INDEX
    Explanations

    instances of the word "ongoing" and its variations, indicating continuous processes or events

    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
    rzy
    -0.08
    ñana
    -0.08
    aren
    -0.07
    prung
    -0.07
    mtree
    -0.07
    CHED
    -0.07
    fish
    -0.07
    olumn
    -0.07
    abbo
    -0.07
     lên
    -0.07
    POSITIVE LOGITS
    /up
    0.07
    341
    0.07
    erta
    0.07
    ive
    0.07
    375
    0.07
    jak
    0.06
    ly
    0.06
    /off
    0.06
    LY
    0.06
    845
    0.06
    Activations Density 0.005%

    No Known Activations