© 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. 127670
    Prev
    Next
    INDEX
    Explanations

    phrases related to intentions regarding future actions

    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
    icity
    -0.07
    olian
    -0.07
    mie
    -0.06
     pů
    -0.06
    VIDEO
    -0.06
    ube
    -0.06
    /index
    -0.06
     Halk
    -0.06
    sson
    -0.06
    adil
    -0.06
    POSITIVE LOGITS
     Compact
    0.06
    drs
    0.06
    ger
    0.05
    compact
    0.05
     mill
    0.05
     atmos
    0.05
    AGER
    0.05
    изнеÑģ
    0.05
    ÏĨή
    0.05
    Compact
    0.05
    Activations Density 0.000%

    No Known Activations