© 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. 15973
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their usages

    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
     Eighth
    -0.06
    _TB
    -0.06
    evenodd
    -0.06
    irma
    -0.06
    ÌĨ
    -0.06
     pornstar
    -0.06
    ýt
    -0.06
     Panama
    -0.06
     Chambers
    -0.06
    ave
    -0.06
    POSITIVE LOGITS
    ึà¸ģ
    0.07
     péri
    0.07
    eken
    0.07
     dig
    0.07
    meli
    0.06
    µ
    0.06
    ếp
    0.06
    pson
    0.06
    ForObject
    0.06
    oven
    0.06
    Activations Density 0.000%

    No Known Activations