© 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. 59340
    Prev
    Next
    INDEX
    Explanations

    instances of derogatory language and discussions of offensive behavior

    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
    ients
    -0.08
    .LayoutStyle
    -0.07
    ÑģÑĤан
    -0.07
    ัà¸Ĺ
    -0.07
     дÑĢÑĥж
    -0.07
    ÙijØ©
    -0.07
    -deals
    -0.07
    èģĶç½ij
    -0.07
    esso
    -0.07
    /MPL
    -0.07
    POSITIVE LOGITS
     desk
    0.06
     dispatch
    0.06
     crack
    0.06
    GetObject
    0.06
    erno
    0.06
     tod
    0.05
     ven
    0.05
    cel
    0.05
     taste
    0.05
     intimate
    0.05
    Activations Density 0.040%

    No Known Activations