© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 40146
    Prev
    Next
    INDEX
    Explanations

    important and significant adjectives used to describe concepts or events

    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
    cai
    -0.07
    ognito
    -0.07
    ught
    -0.07
     Resident
    -0.07
    classCallCheck
    -0.07
    ingleton
    -0.07
    nodoc
    -0.07
    ãĥ³ãĤº
    -0.07
    utter
    -0.06
    atten
    -0.06
    POSITIVE LOGITS
     important
    0.09
     example
    0.09
     another
    0.08
     part
    0.08
     key
    0.08
     most
    0.07
     examples
    0.07
     feature
    0.07
     aspect
    0.07
     one
    0.07
    Activations Density 0.023%

    No Known Activations