© 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. 15-LLAMASCOPE-RES-131K
    11. 1017
    Prev
    Next
    INDEX
    Explanations

    phrases related to instructions or steps in a process

    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
     Guill
    -0.07
     Gim
    -0.06
     awaken
    -0.06
    chine
    -0.06
    loor
    -0.06
     Triple
    -0.06
     cân
    -0.06
     वस
    -0.06
    گرد
    -0.06
    borg
    -0.06
    POSITIVE LOGITS
     Trafford
    0.06
    컵
    0.06
    roph
    0.06
    ollah
    0.06
     Speedway
    0.06
    ازÙĦ
    0.06
     noct
    0.06
    acob
    0.06
    cheduler
    0.06
     ë³´ëĤ´
    0.06
    Activations Density 0.001%

    No Known Activations