© 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. 78600
    Prev
    Next
    INDEX
    Explanations

    phrases that quantify or emphasize multiple instances or variations of something

    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
    que
    -0.07
    ie
    -0.06
     bin
    -0.06
     on
    -0.06
     Aurora
    -0.06
    on
    -0.06
    -bin
    -0.06
    ä¸ĬçļĦ
    -0.06
     Sound
    -0.06
    ital
    -0.06
    POSITIVE LOGITS
     behalf
    0.10
     occasion
    0.09
    eday
    0.08
     grounds
    0.08
    angel
    0.07
     steroids
    0.07
     occasions
    0.07
    åľ¨çº¿éĺħ读
    0.07
    گاÙĨ
    0.07
    occasion
    0.07
    Activations Density 0.049%

    No Known Activations