© 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. 78021
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics, especially related to financial metrics and beverage consumption

    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
    sto
    -0.06
    og
    -0.06
    ind
    -0.06
    ssel
    -0.05
    oin
    -0.05
     M
    -0.05
     cracking
    -0.05
    ()
    -0.05
     =
    -0.05
     undisclosed
    -0.05
    POSITIVE LOGITS
    .newaxis
    0.08
    å¤ĩ注
    0.08
    ENTA
    0.08
     rowspan
    0.08
    VERR
    0.07
     詳細
    0.07
    веÑī
    0.07
    ëį°ìĿ´íĬ¸
    0.07
    #ac
    0.07
    nech
    0.07
    Activations Density 0.047%

    No Known Activations