© 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. 27312
    Prev
    Next
    INDEX
    Explanations

    descriptions of sensitive biological processes and their implications

    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
    497
    -0.06
    644
    -0.06
     pol
    -0.06
    643
    -0.06
     hole
    -0.06
    ãĥ¡ãĥ©
    -0.06
     usage
    -0.06
     ram
    -0.05
     ÙĨÙĤد
    -0.05
    coni
    -0.05
    POSITIVE LOGITS
    _sur
    0.07
    eyed
    0.07
    insi
    0.07
    .Persistent
    0.07
    ience
    0.07
    apon
    0.07
    axter
    0.06
    Surv
    0.06
     survivors
    0.06
    çģŃ
    0.06
    Activations Density 0.004%

    No Known Activations