© 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 EvalsExportsAPI 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. 84240
    Prev
    Next
    INDEX
    Explanations

    instructions related to cooking or baking measurements

    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
     Peace
    -0.06
    ONUS
    -0.06
     Bonus
    -0.06
    oti
    -0.06
     bump
    -0.06
     passive
    -0.06
     cigaret
    -0.06
     peace
    -0.05
     Citizen
    -0.05
    ear
    -0.05
    POSITIVE LOGITS
    çīĮ
    0.07
    #w
    0.07
     proportions
    0.07
    .addTarget
    0.07
    лиÑĤ
    0.07
    Needed
    0.07
    bows
    0.07
    Ñħо
    0.07
    Volumes
    0.07
    uant
    0.07
    Activations Density 0.035%

    No Known Activations