© 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. 5-LLAMASCOPE-RES-131K
    11. 126391
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Luc."

    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
    edly
    -0.08
    543
    -0.08
    emi
    -0.08
    ะ
    -0.08
    εÏĨ
    -0.07
    geois
    -0.07
    heit
    -0.07
    ptrdiff
    -0.07
    erten
    -0.07
    eps
    -0.07
    POSITIVE LOGITS
    us
    0.07
    inox
    0.07
    cth
    0.06
    istically
    0.06
    ally
    0.06
    eto
    0.06
    ly
    0.06
    ail
    0.06
    elli
    0.06
    ively
    0.06
    Activations Density 0.011%

    No Known Activations