© 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. 94584
    Prev
    Next
    INDEX
    Explanations

    references to languages and linguistic origins

    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
    quot
    -0.07
    /tos
    -0.07
    .ss
    -0.07
    riba
    -0.07
    /goto
    -0.07
    idar
    -0.06
    519
    -0.06
    strand
    -0.06
     quotient
    -0.06
     etc
    -0.06
    POSITIVE LOGITS
    -speaking
    0.09
    -Russian
    0.08
    /Dk
    0.07
    -language
    0.07
     words
    0.07
    -spe
    0.07
    -American
    0.07
    -Muslim
    0.07
    DBNull
    0.07
     Franken
    0.07
    Activations Density 0.011%

    No Known Activations