© 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. 57947
    Prev
    Next
    INDEX
    Explanations

    words related to persistence and determination

    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
    ury
    -0.06
    onda
    -0.06
    ings
    -0.06
     Kenn
    -0.05
    FromArray
    -0.05
    #/
    -0.05
     conc
    -0.05
    ums
    -0.05
    opa
    -0.05
     McG
    -0.05
    POSITIVE LOGITS
    cela
    0.07
    ancel
    0.07
    MBER
    0.07
    agus
    0.07
    ãģ£ãģį
    0.07
    alker
    0.07
    ERO
    0.07
    ocup
    0.06
    Disallow
    0.06
    angu
    0.06
    Activations Density 0.009%

    No Known Activations