© 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. 84849
    Prev
    Next
    INDEX
    Explanations

    terms associated with academic or structured analysis, particularly in a research 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
     stuff
    -0.09
    stuff
    -0.08
    Stuff
    -0.08
     Stuff
    -0.07
    åIJĦç§į
    -0.07
     Various
    -0.07
    305
    -0.07
    iagnostics
    -0.07
    869
    -0.07
    Various
    -0.07
    POSITIVE LOGITS
     halves
    0.08
     consecutive
    0.07
     sets
    0.07
    åĪĨåĪ«
    0.07
     continents
    0.06
    sets
    0.06
    secutive
    0.06
    CCC
    0.06
    عاÙĨ
    0.06
     sisters
    0.06
    Activations Density 0.155%

    No Known Activations