© 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. 30097
    Prev
    Next
    INDEX
    Explanations

    phrases that convey necessity or requirements

    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
    ILLE
    -0.07
    rias
    -0.07
    sti
    -0.06
    RICS
    -0.06
    aus
    -0.06
     maintenant
    -0.06
    uib
    -0.06
    iš
    -0.06
     ju
    -0.06
    RIC
    -0.06
    POSITIVE LOGITS
     soon
    0.06
    STR
    0.06
    205
    0.06
    :animated
    0.06
     forthcoming
    0.06
    uren
    0.06
     Soon
    0.06
    TestCase
    0.06
    713
    0.06
    203
    0.06
    Activations Density 0.022%

    No Known Activations