© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 27465
    Prev
    Next
    INDEX
    Explanations

    terms related to legal presentations and proceedings

    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
    .archive
    -0.06
    iros
    -0.06
    zilla
    -0.06
    çĿ£
    -0.06
    alin
    -0.06
     Kickstarter
    -0.06
    /native
    -0.06
     native
    -0.06
    /manual
    -0.05
    à¸Ħร
    -0.05
    POSITIVE LOGITS
    IGH
    0.07
    ynet
    0.07
    ÑĬ
    0.07
    ICH
    0.07
    ách
    0.07
    íĥĦ
    0.07
    éĢŁ
    0.07
    .magic
    0.06
    avid
    0.06
    .fs
    0.06
    Activations Density 0.005%

    No Known Activations