© 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. 41312
    Prev
    Next
    INDEX
    Explanations

    numerical data or statistical outputs

    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
    zek
    -0.08
     del
    -0.06
     trails
    -0.06
     impair
    -0.06
    s
    -0.05
     meats
    -0.05
     cul
    -0.05
    866
    -0.05
    heed
    -0.05
     dap
    -0.05
    POSITIVE LOGITS
    missive
    0.07
    aylight
    0.07
    (assert
    0.07
    677
    0.07
    'icon
    0.06
    EIF
    0.06
     COPYING
    0.06
     اÙĦثاÙĨÙĬØ©
    0.06
    lrt
    0.06
    -valu
    0.06
    Activations Density 0.001%

    No Known Activations