© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 89350
    Prev
    Next
    INDEX
    Explanations

    HTML input attributes and their properties

    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
     circum
    -0.07
    mür
    -0.06
    imuth
    -0.06
    nest
    -0.06
    isoft
    -0.06
    ä¹±
    -0.06
    762
    -0.06
     troub
    -0.06
     intr
    -0.06
    θα
    -0.05
    POSITIVE LOGITS
     birinin
    0.07
    anken
    0.07
     Ori
    0.07
    yntax
    0.07
    .ToUpper
    0.07
     Pike
    0.07
    cts
    0.06
     bli
    0.06
     Aires
    0.06
    .tc
    0.06
    Activations Density 0.004%

    No Known Activations