© 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. 59621
    Prev
    Next
    INDEX
    Explanations

    qualifying adverbs that emphasize degree or extent

    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
    atatype
    -0.07
    опаÑģ
    -0.06
    PRS
    -0.06
    ávÄĽ
    -0.06
    arp
    -0.06
    eni
    -0.06
    ĶåĽŀ
    -0.06
    bean
    -0.06
    orns
    -0.06
     piger
    -0.06
    POSITIVE LOGITS
    ORIZ
    0.07
    SWEP
    0.07
    èļ
    0.06
    usher
    0.06
    cope
    0.06
    Spacer
    0.06
    æļ
    0.06
    mediate
    0.06
    dialogs
    0.06
    ระà¸ļ
    0.06
    Activations Density 0.050%

    No Known Activations