© 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 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. 29381
    Prev
    Next
    INDEX
    Explanations

    phrases associated with financial status and net 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
    ota
    -0.06
     imp
    -0.06
    iesel
    -0.06
    agra
    -0.06
    lag
    -0.05
     competition
    -0.05
    anga
    -0.05
    еж
    -0.05
    ous
    -0.05
    otic
    -0.05
    POSITIVE LOGITS
    ɵ
    0.07
    iÅŁim
    0.07
    алÑĸÑģÑĤ
    0.07
     ++$
    0.07
    acente
    0.07
    .ASCII
    0.07
    arih
    0.07
     porr
    0.07
    DET
    0.06
    iseum
    0.06
    Activations Density 0.004%

    No Known Activations