© 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. 85036
    Prev
    Next
    INDEX
    Explanations

    legal agreements and conditions involving space and responsibilities

    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
    ktor
    -0.06
     selections
    -0.06
    usi
    -0.06
     Mayer
    -0.06
    cher
    -0.06
    ifter
    -0.06
    rer
    -0.06
    ytt
    -0.05
    P
    -0.05
    uw
    -0.05
    POSITIVE LOGITS
     second
    0.12
    第äºĮ
    0.09
    second
    0.09
     segundo
    0.09
     one
    0.09
     druhé
    0.08
    (second
    0.08
     вÑĤоÑĢой
    0.08
     segunda
    0.08
     ikinci
    0.08
    Activations Density 0.055%

    No Known Activations