© 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. 56247
    Prev
    Next
    INDEX
    Explanations

    references to the coronavirus variant "Omicron" and its impact

    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
    .scalablytyped
    -0.09
    ảnh
    -0.08
    .jd
    -0.08
    pedo
    -0.07
    UNS
    -0.07
    peÄį
    -0.07
    acb
    -0.07
    برÛĮ
    -0.07
    YPES
    -0.07
    oi
    -0.07
    POSITIVE LOGITS
     variant
    0.06
     countries
    0.06
     Mour
    0.06
    uba
    0.06
     Variant
    0.06
     spread
    0.06
     laboratories
    0.06
     Goodman
    0.06
     samples
    0.06
     pl
    0.05
    Activations Density 0.014%

    No Known Activations