© 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. 78380
    Prev
    Next
    INDEX
    Explanations

    corporate and administrative details including company names, locations, and document references

    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
    onya
    -0.06
     /
    -0.06
     Forest
    -0.06
    ehler
    -0.06
    uch
    -0.06
    uchar
    -0.06
    emean
    -0.06
     style
    -0.05
    .hr
    -0.05
     iceberg
    -0.05
    POSITIVE LOGITS
     inventions
    0.08
     invention
    0.08
    .sul
    0.07
    :''
    0.07
    tainment
    0.07
    ROUGH
    0.07
    íĮĮíĬ¸
    0.07
    Claim
    0.07
     invent
    0.07
    رÙĬد
    0.07
    Activations Density 0.049%

    No Known Activations