© 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. 77722
    Prev
    Next
    INDEX
    Explanations

    repetitions of the word "bacon"

    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
    ạ
    -0.07
    nell
    -0.07
    Ïģά
    -0.07
     vast
    -0.07
    bab
    -0.07
     *)((
    -0.07
    ÑĢд
    -0.06
    noinspection
    -0.06
    CACHE
    -0.06
    åĴ²
    -0.06
    POSITIVE LOGITS
    stry
    0.09
    ing
    0.07
    Ïħγ
    0.07
    852
    0.07
    ution
    0.07
    iflower
    0.07
     ³³ ³³ ³³ ³³
    0.07
    ess
    0.07
     Alps
    0.07
    ation
    0.07
    Activations Density 0.085%

    No Known Activations