© 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. 15-LLAMASCOPE-RES-131K
    11. 27158
    Prev
    Next
    INDEX
    Explanations

    references to distinct and notable smells

    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
     pace
    -0.07
     peer
    -0.06
     refill
    -0.05
     rational
    -0.05
     Frozen
    -0.05
     Dixon
    -0.05
    estre
    -0.05
    :&
    -0.05
     upgrade
    -0.05
     mÃŃn
    -0.05
    POSITIVE LOGITS
     запаÑħ
    0.09
    ãĤ¯ãĤ»
    0.08
     scent
    0.08
     od
    0.08
     smell
    0.08
    åĨĴ
    0.07
     odor
    0.07
    ateria
    0.07
    atern
    0.07
    iffer
    0.07
    Activations Density 0.031%

    No Known Activations