© 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. 39584
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate future events or potential developments

    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
     recently
    -0.06
     terminal
    -0.06
    uju
    -0.05
    recent
    -0.05
     Recently
    -0.05
    ÏĦÏģ
    -0.05
    âĢ¦↵
    -0.05
     uns
    -0.05
    Recently
    -0.05
    /
    -0.05
    POSITIVE LOGITS
     promising
    0.10
     promise
    0.09
     promises
    0.09
     becoming
    0.09
    promise
    0.09
    cape
    0.08
    Unhandled
    0.08
    agos
    0.08
    idor
    0.08
    licht
    0.08
    Activations Density 0.020%

    No Known Activations