© 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. 60898
    Prev
    Next
    INDEX
    Explanations

    references to dates and timelines associated with events

    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
     Factor
    -0.07
    éłŃ
    -0.06
    rica
    -0.06
    lys
    -0.06
    factor
    -0.06
     ÑĨÑĸй
    -0.06
    ursively
    -0.06
    .getDeclared
    -0.06
    ênh
    -0.06
     æĬķ稿æĹ¥
    -0.06
    POSITIVE LOGITS
    enza
    0.08
    aye
    0.07
    201
    0.07
     March
    0.07
    ohana
    0.07
     June
    0.07
     August
    0.06
     December
    0.06
     February
    0.06
     October
    0.06
    Activations Density 0.010%

    No Known Activations