© 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. 94467
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to become."

    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
    ighth
    -0.07
    ses
    -0.07
     sebou
    -0.07
    åī©
    -0.07
    iry
    -0.07
    omp
    -0.07
    holders
    -0.07
    lots
    -0.07
    quo
    -0.07
    ë§IJ
    -0.07
    POSITIVE LOGITS
     part
    0.09
     a
    0.07
     increasingly
    0.07
     sole
    0.07
    ucz
    0.06
    acons
    0.06
    ãģ¹
    0.06
    icho
    0.06
    375
    0.06
     destinationViewController
    0.06
    Activations Density 0.038%

    No Known Activations