© 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. 16566
    Prev
    Next
    INDEX
    Explanations

    structured data related to configuration settings

    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
    AGMA
    -0.07
     Area
    -0.07
    PEED
    -0.06
    Area
    -0.06
    anders
    -0.06
    ¼åIJĪ
    -0.06
     sou
    -0.06
    annah
    -0.06
     area
    -0.06
    138
    -0.06
    POSITIVE LOGITS
     Shel
    0.07
    leon
    0.07
    ical
    0.07
    âĢ¦↵↵↵
    0.06
    ạp
    0.06
    aucoup
    0.06
    á»ĵi
    0.06
     repetition
    0.06
    dac
    0.06
    ipy
    0.06
    Activations Density 0.008%

    No Known Activations