© 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. 98376
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the presence of specific ingredients or components in products

    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
     kern
    -0.06
    hv
    -0.06
    agoon
    -0.06
    enda
    -0.06
    esc
    -0.06
     Nec
    -0.06
     reinc
    -0.06
    rement
    -0.06
    ibri
    -0.05
    ãĥ¼ãĥ³
    -0.05
    POSITIVE LOGITS
     Millenn
    0.07
    iyon
    0.07
    alic
    0.07
     Moderate
    0.06
    .Relative
    0.06
    ÑŁ
    0.06
    -conf
    0.06
    adena
    0.06
    plib
    0.06
    536
    0.06
    Activations Density 0.038%

    No Known Activations