© 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. 40710
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to legal jargon or official documents

    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
    pter
    -0.06
    abinet
    -0.06
    oter
    -0.06
    er
    -0.06
    elah
    -0.06
    '=>"
    -0.06
    zcze
    -0.06
     ãĤ»
    -0.06
    earch
    -0.06
    ari
    -0.05
    POSITIVE LOGITS
    STYPE
    0.08
    ogg
    0.07
    ocity
    0.07
    اÙĪÙĨد
    0.07
    AMENT
    0.07
     poz
    0.07
    USTER
    0.07
    antino
    0.07
    .Îł
    0.07
    ammen
    0.07
    Activations Density 0.006%

    No Known Activations