© 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 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. 17-LLAMASCOPE-RES-131K
    11. 59077
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to analysis and digital security processes

    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
    ektor
    -0.08
    ONGL
    -0.08
    .TabStop
    -0.07
    istrovstvÃŃ
    -0.07
    еÑĢалÑĮ
    -0.07
    niÄį
    -0.07
    arshal
    -0.07
     pkt
    -0.06
    bero
    -0.06
     {\↵
    -0.06
    POSITIVE LOGITS
     data
    0.10
     propri
    0.08
    data
    0.07
    propri
    0.07
     propriet
    0.07
     proprietary
    0.07
     factors
    0.07
    odata
    0.06
     formula
    0.06
     sources
    0.06
    Activations Density 0.028%

    No Known Activations