© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 40487
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Say" and variations of it in different contexts

    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
    eration
    -0.07
    ugh
    -0.07
    orf
    -0.06
    yte
    -0.06
    bery
    -0.06
    ics
    -0.06
    china
    -0.06
    luv
    -0.06
    sand
    -0.06
     >č↵
    -0.06
    POSITIVE LOGITS
     STDERR
    0.08
    dney
    0.07
    agues
    0.07
    -alist
    0.07
    dust
    0.07
    eg
    0.07
    gili
    0.07
    onnement
    0.07
    ings
    0.07
    един
    0.07
    Activations Density 0.012%

    No Known Activations