© 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. 124344
    Prev
    Next
    INDEX
    Explanations

    acronyms and symbols related to organizations and membership

    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
    lok
    -0.08
    ADDE
    -0.07
    antz
    -0.07
    kem
    -0.07
    inox
    -0.07
    getMock
    -0.07
    ietet
    -0.07
    ãĢħ
    -0.07
    REFERRED
    -0.07
     sexe
    -0.07
    POSITIVE LOGITS
    .org
    0.07
    .COM
    0.07
    .blogspot
    0.06
    emsp
    0.06
    ÂĢÂĻ
    0.06
    entifier
    0.06
    .com
    0.06
    .wordpress
    0.06
    -TV
    0.06
    0.05
    Activations Density 0.107%

    No Known Activations