© 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. 27934
    Prev
    Next
    INDEX
    Explanations

    chemical and biological terms related to food, drink, and cellular structures

    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
    aber
    -0.07
     merc
    -0.06
     Lump
    -0.06
    uais
    -0.06
    yang
    -0.06
    sage
    -0.06
    funcs
    -0.06
    usercontent
    -0.06
    Ùĩ
    -0.06
    inkle
    -0.06
    POSITIVE LOGITS
    sWith
    0.10
    swith
    0.10
    sthrough
    0.09
    sto
    0.08
    sin
    0.07
    们
    0.07
    aceous
    0.07
    Ñķ
    0.07
    ами
    0.07
    Ø´Ùħ
    0.07
    Activations Density 0.118%

    No Known Activations