© 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. 106396
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Laurie."

    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
    ardin
    -0.07
    ardo
    -0.07
    noop
    -0.07
    bour
    -0.07
    oples
    -0.07
    estruction
    -0.07
    NamedQuery
    -0.06
     ola
    -0.06
    ardon
    -0.06
    stones
    -0.06
    POSITIVE LOGITS
     Sever
    0.06
    ollen
    0.06
     же
    0.06
     Kann
    0.06
    ann
    0.06
    é«
    0.06
    oser
    0.06
     Morm
    0.06
    letters
    0.06
    ovid
    0.05
    Activations Density 0.008%

    No Known Activations