© 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. 82678
    Prev
    Next
    INDEX
    Explanations

    actions related to cooking and food preparation

    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
    essen
    -0.07
    330
    -0.07
    aminer
    -0.06
    allet
    -0.06
     Cz
    -0.06
    ente
    -0.06
    é¥
    -0.06
     chalk
    -0.06
    antee
    -0.06
     added
    -0.05
    POSITIVE LOGITS
     mixture
    0.09
    ixture
    0.08
    atsapp
    0.07
     ÑģмеÑģÑĮ
    0.07
     æŃ
    0.07
    ượ
    0.07
    iversal
    0.07
    _BIND
    0.06
    ablish
    0.06
    nÄħ
    0.06
    Activations Density 0.043%

    No Known Activations