© 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. 79367
    Prev
    Next
    INDEX
    Explanations

    phrases that pertain to liability and legal connections

    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
     Sco
    -0.07
    zi
    -0.07
     BOT
    -0.07
     ÎķÏĢ
    -0.06
    insky
    -0.06
    sc
    -0.06
    uesta
    -0.06
    cuts
    -0.06
    oram
    -0.06
    uis
    -0.06
    POSITIVE LOGITS
    .ribbon
    0.07
     Dün
    0.07
    -Origin
    0.07
    å¹¹
    0.06
    ÆĴ
    0.06
    .Matchers
    0.06
    âĢ¡
    0.06
    ì¶ķ
    0.06
    æ··
    0.06
     Duy
    0.06
    Activations Density 0.000%

    No Known Activations