© 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. 61466
    Prev
    Next
    INDEX
    Explanations

    references to software security and validation processes related to application 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
    .sessions
    -0.07
    ÑĥÑģÑĤа
    -0.07
     bergen
    -0.07
    iqu
    -0.07
    ave
    -0.07
    unda
    -0.07
    ë§ī
    -0.07
     Sessions
    -0.07
     å¹³
    -0.06
    esi
    -0.06
    POSITIVE LOGITS
     trust
    0.06
     trusted
    0.06
     contents
    0.06
    ¡
    0.05
    olithic
    0.05
    etz
    0.05
    áng
    0.05
     transit
    0.05
     Quadr
    0.05
     Garland
    0.05
    Activations Density 0.002%

    No Known Activations