© 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. 95825
    Prev
    Next
    INDEX
    Explanations

    references to the Me Too movement and issues related to sexual abuse

    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
     تبÙĦÛĮ
    -0.07
     veget
    -0.07
    lector
    -0.07
    åĪº
    -0.07
     ÑĢÑĸд
    -0.07
     ADVISED
    -0.07
    engo
    -0.07
     amort
    -0.07
    LOAT
    -0.06
     pov
    -0.06
    POSITIVE LOGITS
    osi
    0.06
     movement
    0.06
    erti
    0.06
     Hunter
    0.06
     sexual
    0.06
     industries
    0.06
    818
    0.05
    ioni
    0.05
     threads
    0.05
     thread
    0.05
    Activations Density 0.008%

    No Known Activations