© 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. 41071
    Prev
    Next
    INDEX
    Explanations

    mentions of blogs and social media platforms

    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
    418
    -0.08
    ihar
    -0.07
    aller
    -0.07
    istik
    -0.07
    arium
    -0.07
    ahl
    -0.06
    596
    -0.06
    556
    -0.06
    473
    -0.06
    607
    -0.06
    POSITIVE LOGITS
    -wide
    0.07
    isode
    0.07
    ESA
    0.06
     article
    0.06
    afort
    0.06
    esa
    0.06
    lesc
    0.06
    iteli
    0.06
    errs
    0.06
    /google
    0.06
    Activations Density 0.020%

    No Known Activations