© 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. 17-LLAMASCOPE-RES-131K
    11. 119701
    Prev
    Next
    INDEX
    Explanations

    formal terminology and expressions related to legal and regulatory contexts

    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
    .Execute
    -0.06
    uai
    -0.06
    862
    -0.06
    ALS
    -0.06
     fro
    -0.05
    iver
    -0.05
    ults
    -0.05
    ign
    -0.05
     laid
    -0.05
    uele
    -0.05
    POSITIVE LOGITS
    iges
    0.07
    ahoma
    0.07
     defaultCenter
    0.07
     Erotik
    0.07
    onn
    0.07
    arella
    0.07
    .Slf
    0.07
    IES
    0.07
    erp
    0.06
    agher
    0.06
    Activations Density 0.001%

    No Known Activations