© 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. 73633
    Prev
    Next
    INDEX
    Explanations

    references to regulatory terms and compliance issues

    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
     extras
    -0.06
    .heading
    -0.06
     Reach
    -0.06
    Subview
    -0.06
    uo
    -0.06
     Mare
    -0.06
    isson
    -0.06
     veget
    -0.06
    Reach
    -0.06
    ippo
    -0.06
    POSITIVE LOGITS
    /reference
    0.09
     refer
    0.09
     Refer
    0.09
     reference
    0.08
    Refer
    0.08
     Reference
    0.08
    uide
    0.08
     references
    0.08
    (reference
    0.07
     REFER
    0.07
    Activations Density 0.035%

    No Known Activations