© 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. 39412
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conditions or requirements for actions or decisions

    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
    pector
    -0.08
    康
    -0.07
    urre
    -0.07
    redo
    -0.07
    ķĮ
    -0.07
    å¨ľ
    -0.07
    icerca
    -0.06
    zag
    -0.06
    koli
    -0.06
    avana
    -0.06
    POSITIVE LOGITS
     purchase
    0.11
     eventual
    0.09
     ultimately
    0.09
    purchase
    0.09
     eventually
    0.08
     purchases
    0.08
     decision
    0.08
     purchasing
    0.08
     Purchase
    0.08
     purchased
    0.07
    Activations Density 0.110%

    No Known Activations