© 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. 42027
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal struggles and achievements

    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
    aura
    -0.07
    urdy
    -0.07
    roat
    -0.07
    uiten
    -0.06
    upe
    -0.06
     либо
    -0.06
     Fah
    -0.06
    οκ
    -0.06
    oidal
    -0.06
    EventArgs
    -0.06
    POSITIVE LOGITS
    illy
    0.07
    XL
    0.07
     multin
    0.06
    addir
    0.06
    ylv
    0.06
    .tap
    0.06
    WARE
    0.06
    âĢķâĢķ
    0.06
     bü
    0.06
     recent
    0.06
    Activations Density 0.001%

    No Known Activations