© 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. 89578
    Prev
    Next
    INDEX
    Explanations

    specific key terms or phrases indicative of technical or specialized concepts

    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
    allis
    -0.06
    åĬĽçļĦ
    -0.06
    леж
    -0.06
    arious
    -0.06
    irit
    -0.06
    ãĥ©ãĥ³ãĥī
    -0.06
    alem
    -0.06
     zbo
    -0.06
    aupt
    -0.06
     putchar
    -0.06
    POSITIVE LOGITS
    isode
    0.07
    thinkable
    0.07
    ãĥ¡ãĥ³ãĥĪ
    0.06
    ooks
    0.06
    osaur
    0.06
    369
    0.06
     destinationViewController
    0.06
    æķ¢
    0.06
    ware
    0.06
    dk
    0.06
    Activations Density 0.034%

    No Known Activations