© 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. 27813
    Prev
    Next
    INDEX
    Explanations

    significant plans or initiatives related to collaboration and content development

    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
    леÑĩ
    -0.08
    ADDE
    -0.07
    vox
    -0.07
    ADF
    -0.07
    168
    -0.07
    ær
    -0.07
    tal
    -0.06
    ayer
    -0.06
     RuntimeMethod
    -0.06
    беÑĢ
    -0.06
    POSITIVE LOGITS
     behalf
    0.13
     projects
    0.10
     project
    0.09
     puzzles
    0.08
     Projects
    0.08
    icity
    0.08
    projects
    0.07
    aran
    0.07
    project
    0.07
     fronts
    0.07
    Activations Density 0.033%

    No Known Activations