© 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. 60752
    Prev
    Next
    INDEX
    Explanations

    words or structures related to the concept of completion or conclusion

    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
    utters
    -0.06
    ãĢħ
    -0.06
     Crafts
    -0.06
    ehen
    -0.06
     ниÑħ
    -0.06
    æŶåĢĻ
    -0.06
    /temp
    -0.06
    ÛĮ
    -0.06
    _INIT
    -0.06
    å°
    -0.06
    POSITIVE LOGITS
    ÑģÑĮ
    0.09
    ÑģÑı
    0.09
    ÏĦαι
    0.09
     Ñģобой
    0.09
    -ÑĤаки
    0.08
     ÑģобоÑİ
    0.08
    ÄĻd
    0.07
    frog
    0.06
     siÄĻ
    0.06
    ÅĤo
    0.06
    Activations Density 0.022%

    No Known Activations