© 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. 9-LLAMASCOPE-RES-131K
    11. 97555
    Prev
    Next
    INDEX
    Explanations

    terms related to commerce and trade news

    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
    ysi
    -0.08
    foy
    -0.07
    nesday
    -0.07
    LTR
    -0.07
    vla
    -0.07
    indre
    -0.07
    kowski
    -0.06
    zej
    -0.06
    mî
    -0.06
    edn
    -0.06
    POSITIVE LOGITS
    asers
    0.07
    icia
    0.06
    spi
    0.06
    ritz
    0.06
    illes
    0.06
    åĩ½
    0.06
    rible
    0.06
    -phase
    0.06
    arity
    0.06
    æĤ
    0.06
    Activations Density 0.000%

    No Known Activations