© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 27408
    Prev
    Next
    INDEX
    Explanations

    patterns of consumerism and the impact of business practices

    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
    qli
    -0.07
    ittel
    -0.07
    elles
    -0.07
    .innerHeight
    -0.06
    orns
    -0.06
     Ä°z
    -0.06
    385
    -0.06
    -svg
    -0.06
    outers
    -0.06
    íĻĺ
    -0.06
    POSITIVE LOGITS
    pull
    0.11
     Pull
    0.11
     pull
    0.10
    Pull
    0.10
     pulling
    0.10
     pulled
    0.10
     pulls
    0.10
    _pull
    0.09
    .Pull
    0.09
     draw
    0.07
    Activations Density 0.023%

    No Known Activations