Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43816
    Prev
    Next
    INDEX
    Explanations

    the name "Mary" in various contexts throughout the document

    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
    hower
    -0.08
    GAN
    -0.08
     Hüs
    -0.07
    clair
    -0.07
    vider
    -0.07
     functional
    -0.06
     Functional
    -0.06
    Functional
    -0.06
    hl
    -0.06
    üml
    -0.06
    POSITIVE LOGITS
     Shelley
    0.10
     Tud
    0.09
     Queen
    0.09
     Mag
    0.08
     Quant
    0.07
     Stuart
    0.07
    oref
    0.07
     Benn
    0.07
     Stewart
    0.07
    mag
    0.07
    Activations Density 0.004%

    No Known Activations