© 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. 95445
    Prev
    Next
    INDEX
    Explanations

    corporate entities and their relationships in business 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
    amu
    -0.06
     Bou
    -0.06
    mony
    -0.06
     Abram
    -0.06
    iel
    -0.05
    è¡ĵ
    -0.05
     Clay
    -0.05
    aset
    -0.05
    ighton
    -0.05
    PEC
    -0.05
    POSITIVE LOGITS
    eba
    0.08
    BackColor
    0.07
    ipel
    0.07
    ñana
    0.07
     Fame
    0.07
    ptune
    0.07
    ë°Ķ
    0.07
    madan
    0.07
    Ùĩر
    0.07
    embros
    0.06
    Activations Density 0.018%

    No Known Activations