© 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. 15-LLAMASCOPE-RES-131K
    11. 103937
    Prev
    Next
    INDEX
    Explanations

    instances of specific years mentioned in the text

    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
    currently
    -0.06
    udeau
    -0.06
    oggler
    -0.06
    utan
    -0.06
     currently
    -0.06
    bere
    -0.06
     Prem
    -0.06
    ách
    -0.06
    ัà¸Ļà¸ķ
    -0.06
    odox
    -0.06
    POSITIVE LOGITS
    /on
    0.08
     ÙħÛĮÙĦادÛĮ
    0.07
    iec
    0.07
    adow
    0.07
    isen
    0.07
    ByExample
    0.07
     Agility
    0.07
    adows
    0.07
    tember
    0.07
    hap
    0.06
    Activations Density 0.019%

    No Known Activations