© 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. 30263
    Prev
    Next
    INDEX
    Explanations

    expressions of subjectivity and personal taste

    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
    utin
    -0.10
    /repository
    -0.08
    samp
    -0.08
    atest
    -0.07
    lew
    -0.07
    .sam
    -0.07
    epy
    -0.07
    .debian
    -0.07
    ernote
    -0.07
    egin
    -0.07
    POSITIVE LOGITS
     different
    0.12
     individual
    0.11
     differently
    0.11
     personal
    0.10
    different
    0.09
    ä¸įåIJĮ
    0.09
     everyone
    0.09
     everybody
    0.09
     subjective
    0.09
     individ
    0.08
    Activations Density 0.058%

    No Known Activations