© 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. 86752
    Prev
    Next
    INDEX
    Explanations

    significant punctuation and formatting in academic writing

    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
    ala
    -0.06
     neigh
    -0.06
    coni
    -0.06
    asures
    -0.06
    et
    -0.06
     easy
    -0.06
     minority
    -0.06
    aring
    -0.05
     Wilkinson
    -0.05
     BAD
    -0.05
    POSITIVE LOGITS
     later
    0.10
    later
    0.10
     Later
    0.09
    Later
    0.08
     subsequent
    0.08
    Å¡em
    0.08
    icast
    0.08
     subsequently
    0.08
     further
    0.07
    uitka
    0.07
    Activations Density 0.080%

    No Known Activations