© 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. 93424
    Prev
    Next
    INDEX
    Explanations

    structured information related to parliamentary proceedings or sessions

    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
    enco
    -0.07
    izu
    -0.07
     Trailer
    -0.06
    غات
    -0.06
     uchar
    -0.06
    onis
    -0.06
    unga
    -0.06
    igo
    -0.06
    aml
    -0.06
    pNet
    -0.06
    POSITIVE LOGITS
    Ñĸдно
    0.06
    Defs
    0.06
    Spell
    0.06
    uggle
    0.06
    Fuse
    0.05
    ÑĨеÑĢ
    0.05
     cer
    0.05
    WAR
    0.05
     convention
    0.05
    Convention
    0.05
    Activations Density 0.001%

    No Known Activations