© 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. 15-LLAMASCOPE-RES-131K
    11. 1276
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and periods in sentences

    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
    eed
    -0.07
    oggler
    -0.07
     ?↵
    -0.07
    ing
    -0.07
    uto
    -0.06
    pag
    -0.06
    obus
    -0.06
    .stem
    -0.06
    odium
    -0.06
    ongs
    -0.06
    POSITIVE LOGITS
    #ac
    0.07
     CONTRIBUTORS
    0.07
     Divide
    0.07
     Sanayi
    0.07
    meli
    0.07
    aupt
    0.06
    äºŃ
    0.06
    gether
    0.06
     ì¦
    0.06
    bsite
    0.06
    Activations Density 0.030%

    No Known Activations