© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 3770
    Prev
    Next
    INDEX
    Explanations

    components and ingredients related to materials or substances

    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
     vars
    -0.06
    unky
    -0.06
    Built
    -0.05
    247
    -0.05
     gasoline
    -0.05
     aromatic
    -0.05
     Built
    -0.05
     milano
    -0.05
     Gap
    -0.05
    celain
    -0.05
    POSITIVE LOGITS
     gel
    0.14
     Gel
    0.14
    gel
    0.12
     Thick
    0.10
     guar
    0.10
     agar
    0.09
     gum
    0.09
    cps
    0.09
     thick
    0.09
     Gum
    0.08
    Activations Density 0.017%

    No Known Activations