© 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. 17-LLAMASCOPE-RES-131K
    11. 94373
    Prev
    Next
    INDEX
    Explanations

    tags and attributes related to images and multimedia elements in web content

    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
    acic
    -0.07
    lops
    -0.07
    uro
    -0.07
    s
    -0.07
    arp
    -0.06
    ersen
    -0.06
    sen
    -0.06
     reverse
    -0.06
    reverse
    -0.06
    na
    -0.06
    POSITIVE LOGITS
    ackbar
    0.08
     CONSEQUENTIAL
    0.07
    istring
    0.07
    ijken
    0.07
    алеж
    0.07
     Truy
    0.07
    /gif
    0.07
    rack
    0.07
     nÃło
    0.07
    ayscale
    0.07
    Activations Density 0.001%

    No Known Activations