© 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. 93781
    Prev
    Next
    INDEX
    Explanations

    instances of the word "careful" indicating the need for caution or attention in various contexts

    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
    ongan
    -0.08
    اÙĤ
    -0.07
    aginator
    -0.07
    lux
    -0.06
    jev
    -0.06
    kara
    -0.06
    Certificates
    -0.06
    emoc
    -0.06
    ansen
    -0.06
    inery
    -0.06
    POSITIVE LOGITS
    yyyy
    0.08
    ãĥ³ãĥĩ
    0.07
    454
    0.07
    394
    0.07
     about
    0.06
    ξη
    0.06
    etched
    0.06
    edula
    0.06
    otte
    0.06
    ieri
    0.06
    Activations Density 0.005%

    No Known Activations