© 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. 17-LLAMASCOPE-RES-131K
    11. 29245
    Prev
    Next
    INDEX
    Explanations

    specific terms and phrases associated with abandonment and issues surrounding it

    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
    ãģ¨ãģĭ
    -0.08
    anlık
    -0.08
    åıĬåħ¶
    -0.08
    .SendMessage
    -0.07
     olanlar
    -0.07
    .Automation
    -0.07
    uyla
    -0.07
    маÑĤÑĢива
    -0.07
    ----</
    -0.07
    ãĥªãĥ¼ãĤº
    -0.07
    POSITIVE LOGITS
    Âł
    0.07
     industry
    0.07
     similar
    0.07
     similarly
    0.06
     worldwide
    0.06
     ebenfalls
    0.06
    ">//
    0.06
    ,
    0.06
    lever
    0.06
     universally
    0.06
    Activations Density 0.001%

    No Known Activations