© 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. 9-LLAMASCOPE-RES-131K
    11. 97458
    Prev
    Next
    INDEX
    Explanations

    phrases that express a sense of seriousness or gravity in various contexts

    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
    reon
    -0.09
    .digital
    -0.07
    $__
    -0.07
    ãĥ¼ãĥĵ
    -0.07
    貸
    -0.07
    Helmet
    -0.07
    .scalablytyped
    -0.07
    ekim
    -0.07
    win
    -0.07
    aleur
    -0.07
    POSITIVE LOGITS
     Ful
    0.07
    er
    0.06
    άÏģ
    0.06
    woord
    0.06
    rd
    0.06
    adle
    0.06
    assen
    0.06
     neither
    0.05
     dram
    0.05
    á»ijng
    0.05
    Activations Density 0.005%

    No Known Activations