© 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. 81610
    Prev
    Next
    INDEX
    Explanations

    phrases related to improving quality of life and addressing societal issues

    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
    nist
    -0.06
    ua
    -0.06
     instead
    -0.06
    007
    -0.05
    .gif
    -0.05
    -0.05
    áln
    -0.05
    ex
    -0.05
    qa
    -0.05
     Russ
    -0.05
    POSITIVE LOGITS
    άÏĤ
    0.08
     immediate
    0.08
     personal
    0.07
    Immediate
    0.07
    ignant
    0.07
    ÑĤап
    0.07
    cesso
    0.07
    ProgressHUD
    0.07
    emez
    0.07
    geois
    0.07
    Activations Density 0.020%

    No Known Activations