© 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. 61447
    Prev
    Next
    INDEX
    Explanations

    brand names and product mentions related to technology and automobiles

    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
    کز
    -0.08
    -0.07
    ongsTo
    -0.07
    ़à¥į
    -0.07
    ýt
    -0.07
    .gf
    -0.07
    vla
    -0.07
    abbr
    -0.07
    urn
    -0.06
    оза
    -0.06
    POSITIVE LOGITS
    ilip
    0.07
    757
    0.07
     Tough
    0.06
    -owned
    0.06
    ians
    0.06
    ania
    0.06
     Corporation
    0.05
     logo
    0.05
    avy
    0.05
     corporation
    0.05
    Activations Density 0.006%

    No Known Activations