© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 130177
    Prev
    Next
    INDEX
    Explanations

    personal stories about resilience and the human experience

    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
     LENG
    -0.08
     Widow
    -0.07
    å·
    -0.07
    abin
    -0.07
    langs
    -0.07
    BOSE
    -0.07
    uien
    -0.07
    reste
    -0.07
     ÑĢазд
    -0.07
    itten
    -0.07
    POSITIVE LOGITS
     my
    0.09
     our
    0.08
     meu
    0.07
     mijn
    0.06
    ç»ĻæĪij
    0.06
    ç§ģãģ®
    0.06
     Bart
    0.06
     ours
    0.06
     nosso
    0.06
    antasy
    0.06
    Activations Density 0.003%

    No Known Activations