© 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. 128994
    Prev
    Next
    INDEX
    Explanations

    reports of casualties and deaths

    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
    uli
    -0.08
    æĹıèĩªæ²»
    -0.07
    ippi
    -0.07
    awl
    -0.07
    ÑĢÑıдÑĥ
    -0.07
    gnore
    -0.07
    ulus
    -0.06
    volution
    -0.06
    .ud
    -0.06
    ìĸ´ìĦľ
    -0.06
    POSITIVE LOGITS
    ÑĨÑı
    0.06
     during
    0.06
     anonymously
    0.06
     p
    0.06
     Bain
    0.06
    åħ¶ä¸Ń
    0.06
    s
    0.05
     while
    0.05
     UX
    0.05
    onet
    0.05
    Activations Density 0.013%

    No Known Activations