© 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. 69717
    Prev
    Next
    INDEX
    Explanations

    expressions of doubt or uncertainty related to personal opinions and experiences

    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
    chein
    -0.08
    Äįet
    -0.07
    ousse
    -0.07
    á»IJ
    -0.07
    wahl
    -0.07
    kup
    -0.07
    eshire
    -0.07
    ternet
    -0.07
    ediator
    -0.07
    flen
    -0.07
    POSITIVE LOGITS
     myself
    0.08
     lots
    0.07
    214
    0.06
    elin
    0.06
    centration
    0.06
     wells
    0.06
    ARING
    0.05
    rog
    0.05
     Econ
    0.05
    俺
    0.05
    Activations Density 0.106%

    No Known Activations