© 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. 14647
    Prev
    Next
    INDEX
    Explanations

    phrases related to support and assistance in times of need

    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
    owie
    -0.07
    orama
    -0.06
    注
    -0.06
    ippy
    -0.06
    lavÃŃ
    -0.06
     Hobby
    -0.05
    ÙĪÙī
    -0.05
    кÑĢеÑĤ
    -0.05
    ZN
    -0.05
     Carn
    -0.05
    POSITIVE LOGITS
     whenever
    0.09
     ìĸ¸ìłľ
    0.09
     anytime
    0.09
     accessibility
    0.08
     contact
    0.07
     readily
    0.07
     доÑģÑĤÑĥп
    0.07
     accessible
    0.07
     support
    0.07
    çĶµè¯Ŀ
    0.07
    Activations Density 0.106%

    No Known Activations