© 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. 62104
    Prev
    Next
    INDEX
    Explanations

    phrases and descriptors that indicate intensity and extremes, particularly in the context of experiences or warnings

    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
    lez
    -0.07
    ache
    -0.06
    ZERO
    -0.06
     Cass
    -0.06
    inks
    -0.06
    Zero
    -0.06
    zero
    -0.05
    lo
    -0.05
    anton
    -0.05
     stip
    -0.05
    POSITIVE LOGITS
    everything
    0.07
    bao
    0.07
    alice
    0.07
    áng
    0.07
     gam
    0.07
    inese
    0.07
    croll
    0.07
    yal
    0.07
     kitchen
    0.07
    rella
    0.07
    Activations Density 0.031%

    No Known Activations