© 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. 9-LLAMASCOPE-RES-131K
    11. 95258
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax elements and function calls

    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
    vale
    -0.07
    yg
    -0.07
    eyse
    -0.07
    rupa
    -0.07
    ublisher
    -0.07
    LOPT
    -0.07
    .sb
    -0.06
    flu
    -0.06
    OUCH
    -0.06
    .Ultra
    -0.06
    POSITIVE LOGITS
     attendant
    0.06
    ustr
    0.06
     Bert
    0.05
     Imagine
    0.05
     CD
    0.05
     Ravens
    0.05
    folios
    0.05
     domic
    0.05
    im
    0.05
     Clarkson
    0.05
    Activations Density 0.018%

    No Known Activations