© 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 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. 75038
    Prev
    Next
    INDEX
    Explanations

    phrases suggesting permission or encouragement

    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
    aggi
    -0.07
    urum
    -0.07
    788
    -0.07
    loff
    -0.07
    aison
    -0.07
    unft
    -0.07
     Thumb
    -0.07
    æľĽ
    -0.07
    addock
    -0.06
     Ying
    -0.06
    POSITIVE LOGITS
     Glob
    0.07
    .scalablytyped
    0.06
    achable
    0.06
     fran
    0.06
    tered
    0.06
     glob
    0.06
     Stream
    0.06
    наÑĩ
    0.06
    ÑĢÑĸп
    0.06
     me
    0.06
    Activations Density 0.011%

    No Known Activations