© 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. 72503
    Prev
    Next
    INDEX
    Explanations

    terms related to organization and structured efforts in various 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
     regularly
    -0.07
    ari
    -0.06
    ITTE
    -0.06
    .vaadin
    -0.06
    arella
    -0.06
     monthly
    -0.06
    以åIJİ
    -0.05
    ipse
    -0.05
     distur
    -0.05
    Performed
    -0.05
    POSITIVE LOGITS
     preparations
    0.11
     participating
    0.10
     preparation
    0.10
     prepar
    0.09
     participation
    0.09
    ä»Ĭå¹´
    0.09
     Preparation
    0.09
    à¹Ģà¸ķร
    0.08
    åıĤåĬł
    0.08
    åıĤä¸İ
    0.08
    Activations Density 0.007%

    No Known Activations