© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 57845
    Prev
    Next
    INDEX
    Explanations

    instances of contrast in various contexts

    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
    alet
    -0.08
    istol
    -0.07
     Mej
    -0.07
    bons
    -0.07
    ampa
    -0.07
    uckle
    -0.07
    ÐŁÐļ
    -0.07
    isl
    -0.07
    holder
    -0.07
    ulin
    -0.07
    POSITIVE LOGITS
    ively
    0.12
    ingly
    0.10
    ive
    0.10
    ed
    0.08
    iveness
    0.07
    /op
    0.07
    ual
    0.07
    inge
    0.07
    contrast
    0.06
    sts
    0.06
    Activations Density 0.009%

    No Known Activations