© 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. 55099
    Prev
    Next
    INDEX
    Explanations

    instances of the word "all" or phrases that imply inclusivity

    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
    oot
    -0.07
    inte
    -0.07
    [__
    -0.06
    ocs
    -0.06
    ires
    -0.06
     compensated
    -0.06
    alm
    -0.06
    ud
    -0.06
    aad
    -0.06
    κοÏį
    -0.06
    POSITIVE LOGITS
    ãģ®æĸ¹
    0.07
    #
    0.07
     proceeds
    0.07
    ernals
    0.07
    .XR
    0.07
    :Register
    0.07
    ĨĴ
    0.07
    éĺ´
    0.07
    inflate
    0.06
    ukkit
    0.06
    Activations Density 0.008%

    No Known Activations