© 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. 75562
    Prev
    Next
    INDEX
    Explanations

    references to tangents or tangibility in various 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
    edition
    -0.08
    Į¨
    -0.07
    theless
    -0.07
    uckle
    -0.07
    ì©
    -0.07
    rong
    -0.07
    owed
    -0.06
    enance
    -0.06
    ovice
    -0.06
    è¢ĸ
    -0.06
    POSITIVE LOGITS
    ley
    0.07
    orra
    0.07
    ulton
    0.06
    eline
    0.06
    ential
    0.06
    azzi
    0.06
    ãĥŃãĥ³
    0.06
    acet
    0.06
    ums
    0.06
    ony
    0.06
    Activations Density 0.005%

    No Known Activations