© 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. 93274
    Prev
    Next
    INDEX
    Explanations

    references to legal or judicial contexts and case citations

    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
    ipur
    -0.08
    -urlencoded
    -0.07
    StateChanged
    -0.07
    راÙĤ
    -0.07
    ChangeEvent
    -0.07
     ür
    -0.07
    rak
    -0.06
    ÙģØ´
    -0.06
    esi
    -0.06
    achten
    -0.06
    POSITIVE LOGITS
    assin
    0.06
    urat
    0.06
    achable
    0.06
    197
    0.05
     Alic
    0.05
    ije
    0.05
     gm
    0.05
    Util
    0.05
    ut
    0.05
    maal
    0.05
    Activations Density 0.028%

    No Known Activations