© 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. 82025
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate opting out of something

    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
     hâl
    -0.08
    utin
    -0.08
    afort
    -0.08
     chung
    -0.07
    ume
    -0.07
    edy
    -0.07
    oons
    -0.07
    abi
    -0.07
    bens
    -0.07
    ENSOR
    -0.07
    POSITIVE LOGITS
    /opt
    0.08
     khá»ıi
    0.08
    aidu
    0.07
     participation
    0.06
    æİī
    0.06
    ero
    0.06
     altogether
    0.06
     via
    0.06
    ting
    0.06
     from
    0.06
    Activations Density 0.002%

    No Known Activations