© 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. 15770
    Prev
    Next
    INDEX
    Explanations

    instances of the number "22" and its variations in context

    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
    chsel
    -0.08
    ATALOG
    -0.07
    aru
    -0.07
     newIndex
    -0.07
    atik
    -0.07
    genic
    -0.07
    mür
    -0.07
    ongyang
    -0.07
    翼
    -0.07
    oldur
    -0.07
    POSITIVE LOGITS
    ually
    0.09
    nd
    0.08
    onym
    0.07
    éĸĵ
    0.07
     Serif
    0.06
    -sized
    0.06
    ndef
    0.06
    nish
    0.06
    ably
    0.06
    лоÑĤ
    0.06
    Activations Density 0.027%

    No Known Activations