© 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. 15-LLAMASCOPE-RES-131K
    11. 1238
    Prev
    Next
    INDEX
    Explanations

    requests and intentions related to actions and choices

    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
    nelle
    -0.07
    uft
    -0.07
    tram
    -0.07
    aban
    -0.07
     بÙĪابة
    -0.07
    è«
    -0.07
    ilig
    -0.06
    utut
    -0.06
    imbus
    -0.06
    okol
    -0.06
    POSITIVE LOGITS
     Ramp
    0.06
     instead
    0.06
     Lol
    0.06
    lex
    0.06
    instead
    0.06
    boost
    0.05
    ategy
    0.05
    oplayer
    0.05
     Pent
    0.05
    cken
    0.05
    Activations Density 0.026%

    No Known Activations