© 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. 90748
    Prev
    Next
    INDEX
    Explanations

    instances of numbers and punctuation marks

    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
    orna
    -0.07
    igs
    -0.07
    imeType
    -0.07
    bt
    -0.07
    )((((
    -0.07
     tav
    -0.07
    ffee
    -0.06
    igli
    -0.06
    bett
    -0.06
    irq
    -0.06
    POSITIVE LOGITS
    stor
    0.07
    alink
    0.07
    swers
    0.06
     Blackburn
    0.06
    LastError
    0.06
    IDA
    0.06
    /&
    0.06
     Kes
    0.05
    ceb
    0.05
    tega
    0.05
    Activations Density 0.029%

    No Known Activations