© 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. 17710
    Prev
    Next
    INDEX
    Explanations

    references to a specific online platform and its associated content

    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
     Wikipedia
    -0.07
     lo
    -0.06
    .githubusercontent
    -0.06
    uxe
    -0.06
     tele
    -0.06
    ushi
    -0.06
    Narr
    -0.06
    лÑĥж
    -0.06
    eri
    -0.06
     i
    -0.06
    POSITIVE LOGITS
    @nate
    0.08
    azine
    0.07
     magazine
    0.07
    ellan
    0.07
     LLC
    0.07
     Hindered
    0.07
    .com
    0.07
    @gmail
    0.07
    âĦ
    0.07
    Ĵáŀ
    0.07
    Activations Density 0.036%

    No Known Activations