© 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. 81679
    Prev
    Next
    INDEX
    Explanations

    comparative phrases and expressions of difference or similarity

    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
     ones
    -0.07
    ary
    -0.06
     Mage
    -0.06
    ay
    -0.06
    ing
    -0.06
     &
    -0.06
    ater
    -0.06
     behalf
    -0.06
    vr
    -0.06
    andelier
    -0.05
    POSITIVE LOGITS
     being
    0.09
    being
    0.08
     Being
    0.08
     usual
    0.07
    Being
    0.07
    важа
    0.07
     PIO
    0.07
    conciliation
    0.06
    quam
    0.06
    -being
    0.06
    Activations Density 0.009%

    No Known Activations