© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 56414
    Prev
    Next
    INDEX
    Explanations

    advises related to introducing children to new foods

    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
    æķ
    -0.07
    mus
    -0.07
    azen
    -0.07
     æģ
    -0.06
    atum
    -0.06
     potentially
    -0.06
    clc
    -0.06
    erial
    -0.06
    dex
    -0.06
    asu
    -0.06
    POSITIVE LOGITS
     yourselves
    0.07
     tooth
    0.07
    ÐĴаж
    0.07
     Tooth
    0.07
     ↵↵
    0.07
    arger
    0.07
    .Helper
    0.07
    egov
    0.06
     household
    0.06
    tains
    0.06
    Activations Density 0.007%

    No Known Activations