© 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. 74589
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and definitions

    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
    Themes
    -0.06
    zone
    -0.06
    ÑĤÑĢа
    -0.06
    æĮĻ
    -0.06
    /null
    -0.06
    /native
    -0.06
    lec
    -0.05
    erg
    -0.05
    levance
    -0.05
    theory
    -0.05
    POSITIVE LOGITS
     conventions
    0.11
     Convention
    0.10
     convention
    0.09
    Convention
    0.09
    UsageId
    0.09
    NewProp
    0.09
    odash
    0.08
    Intialized
    0.08
    HeaderCode
    0.08
    istrovstvÃŃ
    0.08
    Activations Density 0.021%

    No Known Activations