© 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. 87705
    Prev
    Next
    INDEX
    Explanations

    references to childcare and related services

    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
    annel
    -0.08
    illez
    -0.07
    -regexp
    -0.07
    ainter
    -0.07
    uzzi
    -0.07
    ittest
    -0.07
    رÙĪج
    -0.06
    anic
    -0.06
    ìĶ
    -0.06
    retch
    -0.06
    POSITIVE LOGITS
     workers
    0.07
    bers
    0.07
     worker
    0.07
    èĤ²
    0.07
    /feed
    0.07
    ersh
    0.07
    ers
    0.07
    er
    0.06
     operators
    0.06
    _workers
    0.06
    Activations Density 0.006%

    No Known Activations