© 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. 9-LLAMASCOPE-RES-131K
    11. 95616
    Prev
    Next
    INDEX
    Explanations

    references to renewable energy and its growth trends

    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
    AsyncResult
    -0.07
    Äį
    -0.07
    innacle
    -0.07
    aster
    -0.06
    aso
    -0.06
    ãģ¤ãģ¶
    -0.06
    [OF
    -0.06
     Chips
    -0.06
    bern
    -0.06
    roup
    -0.06
    POSITIVE LOGITS
    £
    0.07
    reuse
    0.06
    azard
    0.06
     alternative
    0.06
    Reuse
    0.06
     Alternative
    0.06
     standalone
    0.06
     reuse
    0.06
    è®
    0.06
    scaled
    0.06
    Activations Density 0.020%

    No Known Activations