© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 104197
    Prev
    Next
    INDEX
    Explanations

    color codes and styling elements in HTML and CSS

    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
    yz
    -0.06
    ars
    -0.06
    -0.06
    atin
    -0.06
     boss
    -0.05
     mane
    -0.05
    hab
    -0.05
    t
    -0.05
    ant
    -0.05
     pink
    -0.05
    POSITIVE LOGITS
    erais
    0.10
    erna
    0.07
    minor
    0.07
    å¦
    0.07
    thren
    0.07
    IVATE
    0.07
    contributors
    0.07
     Äijón
    0.07
    chsel
    0.07
    олиÑĤ
    0.07
    Activations Density 0.002%

    No Known Activations