© 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. 86245
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly quotes and special characters

    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
    437
    -0.07
    ÑĪев
    -0.07
    adan
    -0.07
    mart
    -0.07
     Bros
    -0.06
    utin
    -0.06
    loff
    -0.06
    hower
    -0.06
    ________________________________
    -0.06
     Normal
    -0.06
    POSITIVE LOGITS
    awner
    0.07
    aterangepicker
    0.07
     Fortune
    0.06
    .axis
    0.06
     Shel
    0.06
    emain
    0.06
    ogue
    0.06
    Ðĩ
    0.06
    itoris
    0.06
    oky
    0.06
    Activations Density 0.004%

    No Known Activations