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

    Neuronpedia

    Jacobian LensNEW
    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. 128768
    Prev
    Next
    INDEX
    Explanations

    phrases expressing hope or aspiration

    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
    iÄĻ
    -0.07
    chron
    -0.07
    icky
    -0.07
    amps
    -0.06
    aidu
    -0.06
    onian
    -0.06
    éļª
    -0.06
    erk
    -0.06
    weis
    -0.06
    ÙĪرÙĬØ©
    -0.06
    POSITIVE LOGITS
    idla
    0.06
    idis
    0.06
    id
    0.06
    à¸ģรรม
    0.06
    ÙĦØŃ
    0.06
     continued
    0.06
     luder
    0.06
    äd
    0.06
     outcome
    0.06
    ipi
    0.06
    Activations Density 0.009%

    No Known Activations