© 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. 63106
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or strong personal opinions

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    isque
    -0.08
    chw
    -0.07
    chein
    -0.07
     atleast
    -0.07
    astes
    -0.07
    ennen
    -0.07
    steen
    -0.07
    iÄħ
    -0.07
    ese
    -0.07
    -0.07
    POSITIVE LOGITS
     anymore
    0.09
     anything
    0.07
     INTERRUPTION
    0.07
    tml
    0.06
     any
    0.06
    TEE
    0.06
    iline
    0.06
    emek
    0.06
    iant
    0.06
    ãĥªãĥ³ãĤ°
    0.06
    Activations Density 0.014%

    No Known Activations