© 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. 128150
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their frequency in various contexts

    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
    arella
    -0.09
    ogan
    -0.08
    à¹ģห
    -0.07
    .toDouble
    -0.07
    .DropDown
    -0.07
    Ñĸдно
    -0.07
    eler
    -0.07
    acea
    -0.07
     Schiff
    -0.07
    IOC
    -0.07
    POSITIVE LOGITS
    ÄĻż
    0.06
    BODY
    0.05
    izik
    0.05
    /lo
    0.05
    ế
    0.05
    agher
    0.05
    issors
    0.05
    ptive
    0.05
     dug
    0.05
    ediator
    0.05
    Activations Density 0.001%

    No Known Activations