© 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. 9-LLAMASCOPE-RES-131K
    11. 95366
    Prev
    Next
    INDEX
    Explanations

    numerical values and measurements within the text

    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
     functional
    -0.07
    igo
    -0.07
     New
    -0.06
     private
    -0.06
     escape
    -0.06
     stream
    -0.06
     tier
    -0.06
     Burl
    -0.06
     En
    -0.06
    oda
    -0.06
    POSITIVE LOGITS
    ÅĻez
    0.08
    Focused
    0.08
     Hlav
    0.08
    osis
    0.07
    ợ
    0.07
    uitka
    0.07
    erez
    0.07
    ลำ
    0.07
    ogui
    0.07
    å¯Ĩ
    0.07
    Activations Density 0.003%

    No Known Activations