© 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. 9-LLAMASCOPE-RES-131K
    11. 96668
    Prev
    Next
    INDEX
    Explanations

    identifiers and numeric values in tabular data or programming contexts

    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
    bing
    -0.06
    isure
    -0.06
    onymous
    -0.06
    ürn
    -0.06
    ching
    -0.06
    apur
    -0.06
    py
    -0.06
    icone
    -0.06
    DTV
    -0.06
    lest
    -0.06
    POSITIVE LOGITS
    ovan
    0.06
     Calder
    0.06
    aison
    0.06
    ëĤĺëĿ¼
    0.06
    caff
    0.06
    каз
    0.06
    à¤Ĥदर
    0.06
    avo
    0.06
    _interfaces
    0.06
    微软éĽħé»ij
    0.06
    Activations Density 0.004%

    No Known Activations