© 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. 126356
    Prev
    Next
    INDEX
    Explanations

    references to the television show "Doctor Who" and the World Health Organization (WHO)

    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
    nya
    -0.08
    ments
    -0.08
    mente
    -0.07
    ural
    -0.07
    égor
    -0.07
    illos
    -0.07
    ayette
    -0.07
    cola
    -0.07
    net
    -0.07
    mented
    -0.07
    POSITIVE LOGITS
    soever
    0.09
    곡
    0.09
     else
    0.08
    oping
    0.08
    ver
    0.07
    ever
    0.07
    abouts
    0.07
    osh
    0.07
    -нибÑĥдÑĮ
    0.07
    ops
    0.07
    Activations Density 0.017%

    No Known Activations