© 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. 56874
    Prev
    Next
    INDEX
    Explanations

    phrases related to evaluating products and their worth

    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
    .gstatic
    -0.07
    aman
    -0.07
     nackte
    -0.07
    #SBATCH
    -0.07
     Carpenter
    -0.07
    ائÙĬØ©
    -0.07
    «ĺ
    -0.06
     Pins
    -0.06
    bek
    -0.06
    Vintage
    -0.06
    POSITIVE LOGITS
     recommendation
    0.08
     recommended
    0.08
    Recommended
    0.07
     Recommended
    0.07
     buy
    0.06
     recommend
    0.06
    recommended
    0.06
    undy
    0.06
     rad
    0.06
     recommending
    0.06
    Activations Density 0.011%

    No Known Activations