© 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. 129153
    Prev
    Next
    INDEX
    Explanations

    references to climate change and its impacts

    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
    verb
    -0.06
     against
    -0.05
     elect
    -0.05
     centre
    -0.05
     cut
    -0.05
     Foreign
    -0.05
    êµ°
    -0.05
     Howe
    -0.05
    dad
    -0.05
     staff
    -0.05
    POSITIVE LOGITS
    à¥įवव
    0.09
    imdi
    0.07
    -UA
    0.07
    meni
    0.07
    agna
    0.07
    ajo
    0.07
    izzy
    0.07
    arhus
    0.07
    entar
    0.07
    endar
    0.07
    Activations Density 0.008%

    No Known Activations