© 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. 73356
    Prev
    Next
    INDEX
    Explanations

    words related to assumption and uncertainty

    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
    IGHL
    -0.09
    itude
    -0.08
    ularity
    -0.08
    aris
    -0.08
    ilde
    -0.07
    borne
    -0.07
    buquerque
    -0.07
    spir
    -0.07
    esian
    -0.07
    anke
    -0.07
    POSITIVE LOGITS
    vely
    0.07
    ptive
    0.07
     innocence
    0.07
     upon
    0.07
    ptions
    0.06
    ingly
    0.06
    ienie
    0.06
    ebi
    0.06
     favour
    0.06
    ritt
    0.06
    Activations Density 0.002%

    No Known Activations