© 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 EvalsExportsinterp-engineNEWAPI 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. 108113
    Prev
    Next
    INDEX
    Explanations

    phrases that initiate explanations, particularly those starting with "For."

    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
    ola
    -0.07
    OLA
    -0.07
    verter
    -0.07
    inine
    -0.07
    ulner
    -0.06
    iki
    -0.06
    inn
    -0.06
    lessly
    -0.06
    lichen
    -0.06
    (Clone
    -0.06
    POSITIVE LOGITS
     instance
    0.11
     example
    0.10
    unately
    0.09
    cing
    0.09
    instance
    0.08
     many
    0.08
    ced
    0.08
    getting
    0.07
     reasons
    0.07
    adil
    0.07
    Activations Density 0.038%

    No Known Activations