© 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. 17-LLAMASCOPE-RES-131K
    11. 127870
    Prev
    Next
    INDEX
    Explanations

    HTML and web-related elements within the text

    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
    ision
    -0.06
    702
    -0.06
    agon
    -0.06
     Howard
    -0.05
    微软éĽħé»ij
    -0.05
     touch
    -0.05
    ussy
    -0.05
    ówn
    -0.05
    из
    -0.05
    lyn
    -0.05
    POSITIVE LOGITS
    istrovstvÃŃ
    0.08
    象
    0.08
    heed
    0.07
    кÑĥлÑı
    0.07
    æħİ
    0.07
    aname
    0.07
    otec
    0.07
    tout
    0.07
    ãĥ«ãĤ¯
    0.07
    'gc
    0.07
    Activations Density 0.010%

    No Known Activations