© 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. 17-LLAMASCOPE-RES-131K
    11. 74984
    Prev
    Next
    INDEX
    Explanations

    significant moments of personal insight or confession

    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
    okable
    -0.07
    /Dk
    -0.06
    ieten
    -0.06
     opport
    -0.06
    clusive
    -0.06
    rir
    -0.06
    ardown
    -0.06
     eg
    -0.06
    ноÑģÑĤ
    -0.06
    ä
    -0.06
    POSITIVE LOGITS
     upon
    0.07
     countless
    0.07
     Upon
    0.07
    upon
    0.06
    /hooks
    0.06
     recently
    0.06
     when
    0.06
     عÙĨدÙħا
    0.06
    åĪ¤
    0.06
     statement
    0.06
    Activations Density 0.035%

    No Known Activations