© 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. 130821
    Prev
    Next
    INDEX
    Explanations

    terms related to equity and its various forms

    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
    ecast
    -0.10
    thood
    -0.08
    ॰
    -0.07
    té
    -0.07
    :.:
    -0.07
    offs
    -0.07
    omics
    -0.07
    tir
    -0.07
    RuntimeObject
    -0.07
    casts
    -0.07
    POSITIVE LOGITS
    adr
    0.07
    ermann
    0.07
    ilibrium
    0.07
    er
    0.06
    etti
    0.06
    anto
    0.06
    igon
    0.06
    ativo
    0.06
    hots
    0.06
     Denn
    0.06
    Activations Density 0.008%

    No Known Activations