© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 105143
    Prev
    Next
    INDEX
    Explanations

    phrases related to business acquisitions and market metrics

    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
    æŁľ
    -0.06
     bail
    -0.06
    ahkan
    -0.06
     [âĢ¦]↵↵
    -0.06
    ãĥ¼ãĥĪ
    -0.06
    413
    -0.05
     además
    -0.05
     concentrating
    -0.05
     ÎĴα
    -0.05
    impan
    -0.05
    POSITIVE LOGITS
    undi
    0.07
    robat
    0.07
    vise
    0.07
    agit
    0.07
    eru
    0.07
    habi
    0.07
    Æ°ng
    0.07
    hazi
    0.07
    WC
    0.06
    wich
    0.06
    Activations Density 0.001%

    No Known Activations