© 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. 30132
    Prev
    Next
    INDEX
    Explanations

    references to graphs and mathematical concepts within scientific 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
     sublic
    -0.07
    SSIP
    -0.07
    Uvs
    -0.07
    ersiz
    -0.07
    @show
    -0.07
    .inc
    -0.06
    ikit
    -0.06
    hill
    -0.06
    igmoid
    -0.06
    illes
    -0.06
    POSITIVE LOGITS
    IME
    0.07
     Aus
    0.07
     Eisen
    0.06
     Vaughan
    0.06
    atted
    0.06
     modular
    0.06
    Ìģt
    0.06
    ibase
    0.06
     Amerik
    0.06
     pun
    0.06
    Activations Density 0.012%

    No Known Activations