© 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. 126556
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions of making, contributing, and developing

    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
     arrayWith
    -0.07
    nung
    -0.07
    sak
    -0.07
    ünchen
    -0.07
    gressor
    -0.07
    (æĹ¥
    -0.07
    icious
    -0.07
     '&#
    -0.07
    /licenses
    -0.07
    cheon
    -0.07
    POSITIVE LOGITS
     their
    0.09
     them
    0.07
     Their
    0.07
     your
    0.07
    leur
    0.06
    jer
    0.06
     they
    0.06
    Their
    0.06
     иÑħ
    0.06
     any
    0.06
    Activations Density 0.305%

    No Known Activations