© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 94324
    Prev
    Next
    INDEX
    Explanations

    repeated references to specific entities or subjects within a context

    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
    ovsky
    -0.07
    ÙĪÙĪ
    -0.07
    än
    -0.07
    uan
    -0.06
    uum
    -0.06
    trak
    -0.06
    *****↵↵
    -0.06
    ãĥªãĥ¼ãĤº
    -0.06
     Others
    -0.06
     such
    -0.06
    POSITIVE LOGITS
     numerator
    0.11
     sexes
    0.10
     lẫn
    0.09
     että
    0.07
     genders
    0.07
     nor
    0.07
    estone
    0.07
     sides
    0.06
    oÅĻ
    0.06
     halves
    0.06
    Activations Density 0.038%

    No Known Activations