© 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. 15-LLAMASCOPE-RES-131K
    11. 88376
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "authors" and its related responsibilities in academic publishing

    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
    ết
    -0.09
    kud
    -0.07
    asket
    -0.07
     shade
    -0.07
    cloth
    -0.07
    meni
    -0.07
    lesen
    -0.07
     mesel
    -0.07
     Kemal
    -0.07
    ázi
    -0.07
    POSITIVE LOGITS
    ship
    0.07
    (s
    0.06
    :id
    0.06
     Moss
    0.06
     stall
    0.05
    íĺģ
    0.05
     present
    0.05
     MOR
    0.05
     ded
    0.05
    _capacity
    0.05
    Activations Density 0.011%

    No Known Activations