© 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. 15-LLAMASCOPE-RES-131K
    11. 61264
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to "mystery."

    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
    ales
    -0.07
    ETA
    -0.07
    igan
    -0.06
    é»İ
    -0.06
    sta
    -0.06
     Gamb
    -0.06
    enn
    -0.06
    shaw
    -0.06
    .scalablytyped
    -0.06
    _vk
    -0.06
    POSITIVE LOGITS
    ariat
    0.08
    gram
    0.08
    andex
    0.07
    ktop
    0.07
    /conf
    0.06
    kowski
    0.06
    undan
    0.06
    shade
    0.06
    303
    0.06
    grams
    0.06
    Activations Density 0.007%

    No Known Activations