© 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. 57623
    Prev
    Next
    INDEX
    Explanations

    phrases or constructs suggesting a sense of inclusion or membership in a larger group or category

    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
     akci
    -0.07
    ÑħодиÑĤÑĮ
    -0.07
     же
    -0.06
    ÙĨÛĮÙĨ
    -0.06
     Aren
    -0.06
     entire
    -0.06
    il
    -0.06
    æķ´ä¸ª
    -0.06
    805
    -0.06
    (exports
    -0.06
    POSITIVE LOGITS
     different
    0.09
    different
    0.09
     dozen
    0.08
     sclerosis
    0.08
    -purpose
    0.07
     other
    0.07
     Morr
    0.07
    ä¸įåIJĮçļĦ
    0.07
     differently
    0.07
    terr
    0.07
    Activations Density 0.038%

    No Known Activations