© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 57303
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and function words in contexts indicating emphasis or support

    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
    ela
    -0.07
    uzzi
    -0.07
    áš
    -0.06
    -0.06
    -Mart
    -0.06
    æĤł
    -0.06
    uft
    -0.06
    ampil
    -0.06
    TK
    -0.06
    ̧
    -0.06
    POSITIVE LOGITS
    ESIS
    0.07
    braco
    0.07
     –↵↵
    0.07
    Ế
    0.07
     mev
    0.06
    است
    0.06
    _DAC
    0.06
     Rencontre
    0.06
     meis
    0.06
    esis
    0.06
    Activations Density 0.010%

    No Known Activations