© 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. 119133
    Prev
    Next
    INDEX
    Explanations

    phrases related to exacerbation or worsening conditions

    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
    .Companion
    -0.07
    orate
    -0.07
    è¥
    -0.07
    wand
    -0.07
    orney
    -0.06
    duk
    -0.06
    å²³
    -0.06
    rug
    -0.06
    ivity
    -0.06
    368
    -0.06
    POSITIVE LOGITS
     already
    0.10
     existing
    0.10
     Already
    0.10
    already
    0.09
    Already
    0.08
    -existing
    0.08
     conditions
    0.07
     Existing
    0.07
     giÃł
    0.07
    çļĦéĹ®é¢ĺ
    0.07
    Activations Density 0.015%

    No Known Activations