© 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. 28311
    Prev
    Next
    INDEX
    Explanations

    concepts related to learning and therapeutic techniques

    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
    zap
    -0.07
    ifix
    -0.07
    emand
    -0.06
    wish
    -0.06
    ipi
    -0.06
    lou
    -0.06
     bundle
    -0.06
    scr
    -0.06
    hog
    -0.06
    ipo
    -0.06
    POSITIVE LOGITS
     Lifestyle
    0.09
     lifestyle
    0.08
    CLIENT
    0.06
     УкÑĢаÑĹн
    0.06
     Bbw
    0.06
    ITTE
    0.06
    BYTES
    0.06
    æĮĩ导
    0.06
     roman
    0.06
     instr
    0.06
    Activations Density 0.009%

    No Known Activations