© 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. 127887
    Prev
    Next
    INDEX
    Explanations

    terms related to financial and administrative processes

    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
     almost
    -0.07
    anche
    -0.06
     chứ
    -0.06
    defgroup
    -0.06
    esign
    -0.06
     Nam
    -0.06
    iction
    -0.06
    лÑİб
    -0.06
    ialog
    -0.06
    adh
    -0.06
    POSITIVE LOGITS
     nor
    0.09
     sondern
    0.08
    yet
    0.08
     yet
    0.08
    perhaps
    0.07
    æĪĸèĢħ
    0.07
    UNT
    0.07
     or
    0.07
     but
    0.07
    nor
    0.07
    Activations Density 0.033%

    No Known Activations