© 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. 9-LLAMASCOPE-RES-131K
    11. 95885
    Prev
    Next
    INDEX
    Explanations

    references to the 'next' action or progression in a sequence, particularly in contexts involving guidance or instructions

    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
    /tos
    -0.07
    nic
    -0.06
     mighty
    -0.06
    urat
    -0.06
    /weather
    -0.06
    ventus
    -0.06
    /lg
    -0.06
    ná
    -0.06
     nic
    -0.06
    baugh
    -0.06
    POSITIVE LOGITS
    ÑĢаниÑĨ
    0.07
    gage
    0.07
     Lilly
    0.07
    iales
    0.06
    ugin
    0.06
    ragon
    0.06
    è³
    0.06
    aeper
    0.06
     Marriott
    0.06
     Garn
    0.06
    Activations Density 0.001%

    No Known Activations