© 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. 3833
    Prev
    Next
    INDEX
    Explanations

    phrases indicating events or experiences

    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
    yn
    -0.07
    odia
    -0.07
    δά
    -0.07
    hausen
    -0.07
    리ìĸ´
    -0.07
    elay
    -0.07
    ormsg
    -0.07
    ernals
    -0.07
    iola
    -0.07
    elyn
    -0.07
    POSITIVE LOGITS
     kind
    0.09
    kind
    0.08
     sorts
    0.08
    -kind
    0.07
     sort
    0.07
     its
    0.07
     form
    0.06
     ever
    0.06
    lle
    0.06
     anywhere
    0.06
    Activations Density 0.017%

    No Known Activations