© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 126707
    Prev
    Next
    INDEX
    Explanations

    infinitive verbs and phrases indicating intention or purpose

    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
    uisse
    -0.08
    atak
    -0.07
    aida
    -0.07
    ogn
    -0.07
    ewis
    -0.07
     surre
    -0.07
    ahan
    -0.06
    ivol
    -0.06
    اÙĦات
    -0.06
    culate
    -0.06
    POSITIVE LOGITS
     become
    0.07
     pursue
    0.07
    illa
    0.06
    ILLA
    0.06
     inf
    0.06
    odes
    0.06
    DR
    0.06
     Devil
    0.06
     Gam
    0.06
     GS
    0.06
    Activations Density 0.014%

    No Known Activations