© 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. 120885
    Prev
    Next
    INDEX
    Explanations

    concepts related to measurement and change in scientific contexts

    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
    urum
    -0.07
    ugar
    -0.07
    象
    -0.07
    fty
    -0.07
    peer
    -0.06
    åĪļ
    -0.06
    _preference
    -0.06
    nutÃŃ
    -0.06
    DRAM
    -0.06
    .rc
    -0.06
    POSITIVE LOGITS
    stellung
    0.07
    ynchronously
    0.07
     Parameters
    0.07
     parameters
    0.07
     Prices
    0.06
    ÑĢÑĮ
    0.06
    'gc
    0.06
     Ipsum
    0.06
    /change
    0.06
     prices
    0.06
    Activations Density 0.069%

    No Known Activations