© 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 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. 130326
    Prev
    Next
    INDEX
    Explanations

    future-oriented language expressing intentions or promises

    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
     Cumhur
    -0.07
    locker
    -0.07
     поба
    -0.07
    áš
    -0.07
    oplayer
    -0.07
    Ïĥμα
    -0.07
    ÐIJÑĢÑħÑĸв
    -0.07
    Ģë¡ľ
    -0.07
    ichel
    -0.07
    ialect
    -0.07
    POSITIVE LOGITS
     learn
    0.07
     learns
    0.07
     learned
    0.07
    chwitz
    0.07
     gain
    0.06
    åıĹåĪ°
    0.06
    cad
    0.06
     Learn
    0.06
     receive
    0.06
    ol
    0.06
    Activations Density 0.012%

    No Known Activations