© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 123524
    Prev
    Next
    INDEX
    Explanations

    phrases related to uncertainty and potential outcomes

    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
    ropolis
    -0.06
     Pyramid
    -0.06
    تا
    -0.06
    _parms
    -0.06
    baugh
    -0.06
    Ïĥα
    -0.06
    xia
    -0.06
    Ư
    -0.06
    nze
    -0.06
    .TypeOf
    -0.06
    POSITIVE LOGITS
     Cue
    0.07
    ibilit
    0.07
     foreign
    0.07
     cue
    0.06
    ALSE
    0.06
    eli
    0.06
     dag
    0.06
     secular
    0.06
    inski
    0.06
    lig
    0.06
    Activations Density 0.012%

    No Known Activations