© 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. 108611
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal experiences and emotions

    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
    ardu
    -0.08
    strand
    -0.08
    iani
    -0.07
    odyn
    -0.07
    ÏĦιÏĥ
    -0.06
    isku
    -0.06
    algo
    -0.06
     ****************************************************************************
    -0.06
     goof
    -0.06
    ยา
    -0.06
    POSITIVE LOGITS
     picking
    0.07
     stopping
    0.07
    éģĩ
    0.07
     everywhere
    0.07
    é¦
    0.07
     Dabei
    0.07
     pick
    0.07
    stops
    0.07
    ilan
    0.06
     encountering
    0.06
    Activations Density 0.047%

    No Known Activations