© 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. 105075
    Prev
    Next
    INDEX
    Explanations

    closing parentheses and quotation marks in functional code structure

    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
    ellas
    -0.07
    eliness
    -0.07
    ænd
    -0.07
    ipment
    -0.07
    avanaugh
    -0.06
    iene
    -0.06
    mite
    -0.06
    çĨĬ
    -0.06
    peror
    -0.06
    licative
    -0.06
    POSITIVE LOGITS
     if
    0.10
    if
    0.07
     If
    0.07
    	if
    0.07
    468
    0.06
    742
    0.06
    _UNS
    0.06
    212
    0.06
     UIB
    0.06
    çµ
    0.06
    Activations Density 0.004%

    No Known Activations