© 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. 39702
    Prev
    Next
    INDEX
    Explanations

    occurrences of language use and communication experiences across different languages

    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
    ruk
    -0.07
    âĦĸâĦĸ
    -0.07
    yre
    -0.07
    zych
    -0.07
    lut
    -0.07
    å¥ı
    -0.07
    Ñıн
    -0.07
    GIN
    -0.06
    ÅĤo
    -0.06
    upert
    -0.06
    POSITIVE LOGITS
    交æµģ
    0.07
    ocab
    0.06
    eya
    0.06
     conversation
    0.06
     equivalents
    0.06
     bona
    0.06
    449
    0.06
     tapered
    0.06
    bil
    0.06
    portun
    0.06
    Activations Density 0.010%

    No Known Activations