Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 4881
    Prev
    Next
    INDEX
    Explanations

    terminologies related to micronutrients and their significance

    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
    inton
    -0.07
    ê°IJ
    -0.07
    ityEngine
    -0.07
    acomment
    -0.07
    porto
    -0.06
     Cum
    -0.06
    zar
    -0.06
    /GPL
    -0.06
    erece
    -0.06
    scape
    -0.06
    POSITIVE LOGITS
    ucle
    0.12
    ized
    0.08
    yms
    0.08
    eer
    0.08
    -sized
    0.07
    esian
    0.07
    ¨
    0.07
    ews
    0.07
    usp
    0.07
    ised
    0.07
    Activations Density 0.001%

    No Known Activations