© 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. 118742
    Prev
    Next
    INDEX
    Explanations

    references to legal proceedings and sentencing outcomes

    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
     âĹĦ
    -0.08
    uchs
    -0.08
     Dud
    -0.07
    eyen
    -0.07
    uyo
    -0.07
    spy
    -0.07
    uds
    -0.07
    unctuation
    -0.07
    Periph
    -0.07
    éĺħ读次æķ°
    -0.07
    POSITIVE LOGITS
     sentencing
    0.11
     sentence
    0.09
     Sent
    0.08
     sentences
    0.07
     sentenced
    0.07
    auer
    0.07
    Sent
    0.07
     Sentence
    0.06
    sent
    0.06
     mitig
    0.06
    Activations Density 0.009%

    No Known Activations