© 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. 38694
    Prev
    Next
    INDEX
    Explanations

    positive experiences or sentiments related to engaging with others

    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
    ores
    -0.07
    iko
    -0.06
    eli
    -0.06
    icas
    -0.06
    upil
    -0.06
    æģµ
    -0.06
    elan
    -0.06
    anny
    -0.06
    ephy
    -0.06
     ante
    -0.06
    POSITIVE LOGITS
     even
    0.08
     simply
    0.07
    thers
    0.07
    Even
    0.07
    IBUT
    0.07
    essage
    0.07
     interest
    0.07
    414
    0.06
     general
    0.06
    patches
    0.06
    Activations Density 0.031%

    No Known Activations