© 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. 5066
    Prev
    Next
    INDEX
    Explanations

    references to health-conscious choices and values in food and lifestyle

    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
     apart
    -0.07
    NotAllowed
    -0.07
     Bis
    -0.06
     circ
    -0.06
    ãĥ¼ãĤ¹ãĥĪ
    -0.06
    TON
    -0.06
     cade
    -0.06
    allel
    -0.06
    _utf
    -0.06
    vented
    -0.06
    POSITIVE LOGITS
     quantity
    0.09
    quantity
    0.08
     sacrificed
    0.07
    icher
    0.07
     sacrificing
    0.07
     rather
    0.07
     volume
    0.07
     Quantity
    0.07
    rather
    0.07
    $MESS
    0.07
    Activations Density 0.033%

    No Known Activations