© 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. 95850
    Prev
    Next
    INDEX
    Explanations

    phrases expressing inevitability or future events

    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
    rips
    -0.07
     Hills
    -0.07
    berman
    -0.07
    umas
    -0.07
    ICA
    -0.07
    ogui
    -0.07
    emez
    -0.07
    ÑĢеÑģ
    -0.07
    .deb
    -0.06
    ica
    -0.06
    POSITIVE LOGITS
     eventually
    0.10
     soon
    0.10
     Eventually
    0.09
     eventual
    0.09
     Soon
    0.09
    Soon
    0.08
     sooner
    0.08
    Eventually
    0.08
     never
    0.08
    soon
    0.07
    Activations Density 0.059%

    No Known Activations