© 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. 62601
    Prev
    Next
    INDEX
    Explanations

    structured data formats or programming element definitions

    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
    æŀĿ
    -0.06
    æŀ
    -0.06
    934
    -0.06
     Secrets
    -0.06
     planning
    -0.06
     choices
    -0.05
     personal
    -0.05
    halt
    -0.05
     Carb
    -0.05
     carb
    -0.05
    POSITIVE LOGITS
     description
    0.15
    Description
    0.12
     descriptions
    0.12
    description
    0.12
     definition
    0.11
    _DESCRIPTION
    0.11
    _description
    0.11
    .description
    0.11
     Description
    0.11
    	description
    0.11
    Activations Density 0.137%

    No Known Activations