© 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. 104634
    Prev
    Next
    INDEX
    Explanations

    instances of contrast or opposition expressed with "but."

    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
    illo
    -0.08
    enal
    -0.07
    esel
    -0.07
    ÌĨ
    -0.06
     Still
    -0.06
    agle
    -0.06
    彩
    -0.06
     still
    -0.06
    uba
    -0.06
    awl
    -0.06
    POSITIVE LOGITS
     Impossible
    0.08
    Impossible
    0.07
    kle
    0.06
     dafür
    0.06
     imposs
    0.06
    currently
    0.06
    isnan
    0.06
    åıĪ
    0.06
    Blocked
    0.06
    åħĪ
    0.06
    Activations Density 0.027%

    No Known Activations