© 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. 62233
    Prev
    Next
    INDEX
    Explanations

    stress and difficulty related to sleep and anxiety

    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
    errick
    -0.07
    atron
    -0.07
    avs
    -0.07
    .ads
    -0.07
    ilon
    -0.07
    /lists
    -0.06
    .rf
    -0.06
    ãĥ³ãĥij
    -0.06
    outes
    -0.06
    abbo
    -0.06
    POSITIVE LOGITS
     peace
    0.08
     normal
    0.07
    peace
    0.07
     sleep
    0.07
     quiet
    0.07
     escape
    0.07
     privacy
    0.07
    оÑĢÑıд
    0.06
    andid
    0.06
     Ingram
    0.06
    Activations Density 0.043%

    No Known Activations