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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 57699
    Prev
    Next
    INDEX
    Explanations

    actions related to quality assurance and operational effectiveness

    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
     Unters
    -0.06
     Tanner
    -0.06
     fancy
    -0.06
    ا
    -0.06
     ern
    -0.06
    igner
    -0.06
     Lambert
    -0.06
    rst
    -0.06
    inand
    -0.06
    åĬ¨çĶŁæĪIJ
    -0.06
    POSITIVE LOGITS
     mutual
    0.10
     respectively
    0.08
     mutually
    0.08
     respective
    0.07
     Mutual
    0.07
    åħ±åIJĮ
    0.07
    ucer
    0.07
     Kurum
    0.07
    év
    0.07
     smooth
    0.07
    Activations Density 0.032%

    No Known Activations